ieeexplore.ieee.org
Open in
urlscan Pro
2a02:26f0:11a:38d::603
Public Scan
URL:
https://ieeexplore.ieee.org/document/8908695
Submission: On March 03 via manual from BR — Scanned from DE
Submission: On March 03 via manual from BR — Scanned from DE
Form analysis 1 forms found in the DOM
<form _ngcontent-cct-c471="" novalidate="" class="search-bar-wrapper ng-untouched ng-pristine ng-valid">
<div _ngcontent-cct-c471="" class="drop-down d-flex"><label _ngcontent-cct-c471=""><select _ngcontent-cct-c471="" aria-label="content type dropdown" class="pe-4">
<option _ngcontent-cct-c471="">All</option>
<option _ngcontent-cct-c471="">Books</option>
<option _ngcontent-cct-c471="">Conferences</option>
<option _ngcontent-cct-c471="">Courses</option>
<option _ngcontent-cct-c471="">Journals & Magazines</option>
<option _ngcontent-cct-c471="">Standards</option>
<option _ngcontent-cct-c471="">Authors</option>
<option _ngcontent-cct-c471="">Citations</option><!---->
</select></label></div>
<div _ngcontent-cct-c471="" class="search-field all">
<div _ngcontent-cct-c471="" class="search-field-icon-container">
<div _ngcontent-cct-c471="" class="global-search-bar"><xpl-typeahead-migr _ngcontent-cct-c471="" placeholder="" name="search-term" statsclassname="stats-Global_Search_Type_Dropdown"
ulclass="search-within-results ui-autocomplete ui-front ui-menu ui-widget ui-widget-content ui-corner-all" minchars="3" _nghost-cct-c76="">
<div _ngcontent-cct-c76="" class="Typeahead text-sm-md-lh"><input _ngcontent-cct-c76="" type="text" autocomplete="off" aria-label="Enter search text" class="Typeahead-input ng-untouched ng-pristine ng-valid" placeholder=""><!----></div>
</xpl-typeahead-migr></div><!----><!---->
<div _ngcontent-cct-c471="" class="search-icon"><button _ngcontent-cct-c471="" type="submit" aria-label="Search" class="fa fa-search stats-Global_Search_Icon"
data-tealium_data="{"searchTerm": "", "searchType": "all"}"></button></div><!---->
</div><!---->
</div>
</form>Text Content
IEEE websites place cookies on your device to give you the best user experience.
By using our websites, you agree to the placement of these cookies. To learn
more, read our Privacy Policy.
Accept & Close
Skip to Main Content
* IEEE.org
* IEEE Xplore
* IEEE SA
* IEEE Spectrum
* More Sites
SUBSCRIBE
*
SUBSCRIBE
* Cart
*
*
* Create Account
* Personal Sign In
* Browse
* My Settings
* Help
Institutional Sign In
Institutional Sign In
AllBooksConferencesCoursesJournals & MagazinesStandardsAuthorsCitations
ADVANCED SEARCH
Journals & Magazines >IEEE Access >Volume: 7
MULTI-CRITERIA REVIEW-BASED RECOMMENDER SYSTEM–THE STATE OF THE ART
Publisher: IEEE
Cite This
PDF
Sumaia Mohammed Al-Ghuribi; Shahrul Azman Mohd Noah
All Authors
View Document
31
Paper
Citations
6307
Full
Text Views
Open Access
Comment(s)
*
*
*
*
* Alerts
ALERTS
Manage Content Alerts
Add to Citation Alerts
Under a Creative Commons License
--------------------------------------------------------------------------------
Abstract
Document Sections
* I.
Introduction
* II.
Recommender System Approaches
* III.
Multi-Criteria Recommender System
* IV.
User-Generated Reviews
* V.
Multi-Criteria Review-Based Recommendation Approach
Show Full Outline
Authors
Figures
References
Citations
Keywords
Metrics
More Like This
* Download PDF
* View References
*
* Request Permissions
* Save to
* Alerts
Multi-Criteria RS with Users Reviews.
Abstract:In recent times, the recommender systems (RSs) have considerable
importance in academia, commercial activities, and industry. They are widely
used in various domains such...View more
Metadata
Abstract:
In recent times, the recommender systems (RSs) have considerable importance in
academia, commercial activities, and industry. They are widely used in various
domains such as shopping (Amazon), music (Pandora), movies (Netflix), travel
(TripAdvisor), restaurant (Yelp), people (Facebook), and articles (TED). Most of
the RSs approaches rely on a single-criterion rating (overall rating) as a
primary source for the recommendation process. However, the overall rating is
not enough to gain high accuracy of recommendations because the overall rating
cannot express fine-grained analysis behind the user’s behavior. To solve this
problem, multi-criteria recommender systems (MCRSs) have been developed to
improve the accuracy of the RS performance. Additionally, a new source of
information represented by the user-generated reviews is incorporated in the
recommendation process because of the rich and numerous information included
(i.e. review elements) related to the whole item or to a certain feature of the
item or the user’s preferences. The valuable review elements are extracted using
either text mining or sentiment analysis. MCRSs benefit from the review elements
of the user-generated reviews in building their criteria forming multi-criteria
review based recommender systems. The review elements improve the accuracy of
the RS performance and mitigate most of the RS’s problems such as the cold start
and sparsity. In this review, we focused on the multi-criteria review-based
recommender system and explained the user reviews elements in detail and how
these can be integrated into the RSs to help develop their criteria to enhance
the RSs performance. Finally, based on the survey, we presented four future
trends based on this type of RSs to support researchers who wish to pursue
studies in this area.
Published in: IEEE Access ( Volume: 7)
Page(s): 169446 - 169468
Date of Publication: 21 November 2019
Electronic ISSN: 2169-3536
INSPEC Accession Number: 19177368
DOI: 10.1109/ACCESS.2019.2954861
Publisher: IEEE
Funding Agency:
Multi-Criteria RS with Users Reviews.
Hide Full Abstract
Contents
--------------------------------------------------------------------------------
CCBY - IEEE is not the copyright holder of this material. Please follow the
instructions via https://creativecommons.org/licenses/by/4.0/ to obtain
full-text articles and stipulations in the API documentation.
SECTION I.
INTRODUCTION
At present, there is a vast flow of information on the Web, and it continues to
grow exponentially while providing users or customers with various resources
pertaining to services such as products, hotels, and restaurants. Despite the
benefits of such data, the vast flow of information causes challenges for users
to deal with and choose from a huge number of options made available to them.
This causes an information overload problem [1] and makes the decision-making
process more complex. In this case, it is important to filter the information to
a limited amount based on the current user/customer preferences in order to
assist them in making the correct decision [2]. Such a filtering process is
typically done by RSs, which are developed to solve the information overload
problem by providing personalized suggestions of services (i.e. items) to
specific customers according to their preferences [3].
RS has been proven to be significantly crucial in many fields and is widely used
by various domains such as shopping (Amazon), music (Pandora), movies (Netflix),
travel (TripAdvisor), restaurant (Yelp), people (Facebook) and articles (TED).
There are many definitions of RSs including:
1. A tool to mine items and/or collect users’ opinions to help users in their
search process and suggests items related to their preferences [2], [4],
[5].
2. A program or software for content filtering that attempts to reduce the
information overload problem, where users encountered a flood of data on the
Web, by recommending personalized items to users depending on the items’
information and/or users’ preferences [6]–[8].
3. A system to manage information overload problem by collecting information,
guiding users in a personalized way and providing individualized
recommendations as output when there are many possible alternatives to
choose from [9].
The problem of RSs can be identified as a way to assist users/customers to
discover relevant items to suit their needs and most likely to their preferences
[10]. Generally, a model of RS consists of two sets and a utility function, in
which Users set contains all the users and Items set contains all the items that
can be recommended to the users. The utility function calculates the suitability
of a recommendation to a user u∈ Users an item i∈ Items, which is declared as R:
Users × Items → R0, where R0 is equal to either a real number or a positive
integer within a specific range [11].
Typically, RS works through three phases [11]–[13] as follows:
1. Modeling Phase: This phase is focused on preparing the data that will be
used in the next two phases. There are three cases for that, the first is
building a rating matrix that contains the users as rows, items as columns
and the value of each matrix’s cell is the rating done by a user for a
certain item. Second, building a user profile which is mostly a vector for
each user that explains his preferences of an item as a whole or on some
aspects of the item. Third, building an item profile that contains the
features of a specific item.
2. Prediction Phase: This phase aims to predict the rating or score of
unseen/unknown items for a specific user through a utility function
depending on the extracted information during the modeling phase.
3. Recommendation Phase: This phase is an extension of the prediction phase
where various approaches are applied to support the user’s decision by
filtering the most suitable items. It recommends/proposes new items to the
user (i.e. a set of top-N items with the highest-predicted ratings) that is
most likely to be interesting to him.
Figure 1 shows the three main phases of RS.
FIGURE 1.
The phases of recommender system.
Show All
There are three main recommendation approaches which are content-based,
collaborative-based and hybrid. Classical approaches rely on the users’ ratings
as the main source of input of the recommendation. Relying on a single-criterion
(i.e. overall) rating for a recommendation is insufficient to give an accurate
recommendation because the overall ratings cannot express fine-grained analysis
behind the users’ behaviors since it only expresses the coarse-grained analysis.
It cannot be determined why the user choose such ratings. Thus, it is difficult
to know the exact user’s preferences. As a result, multiple-criteria decision
analysis is combined with RS to form a multi-criteria recommender system (MCRS),
in which the recommendation is based on multiple criteria, and not just on a
single criterion.
Besides the primary source (i.e. numeric rating) of the recommendation input,
the user-generated reviews are also used as an alternative source because of the
valuable and rich information they contained. The rich information from the
reviews can be extracted as elements such as topics, features, overall score,
and context, through analyzing the reviews using sentiment analysis or text
analytics approaches. In this survey, we emphasized on MCRS especially in a
multi-criteria review-based RS because of its effective role in enhancing the
accuracy of the RS performance.
In the following content, the state-of-the-art is organized as follows: the RS
approaches are described in Section 2, then the multi-criteria recommender
system is explained in Section 3. After that, in Section 4, the user-generated
reviews and the valuable elements that can be extracted from them are discussed.
This is followed by Section 5 which is the main section because it contains the
most recent researches in the multi-criteria review based recommender system
approaches. Finally, the discussion and the forthcoming trends in MCRS are
presented in Section 6 followed by the conclusion in Section 7.
SECTION II.
RECOMMENDER SYSTEM APPROACHES
Approaches to the recommendation are usually categorized into four categories
which include content-based, collaborative filtering, knowledge-based and
hybrid.
A. CONTENT-BASED APPROACH
A content-based (CB) approach mines the appropriate recommendations for a user
based on his recent behaviors according to what the user liked, bought or
watched [14]. It generates the user profile from previously selected items by
characterizing the user according to the item features and recommends items to
the user based on the items that have similar features to the items that the
user liked before [15]. It characterizes each user without having to compare his
preferences to other users. Put differently, it does not use the information
about other users’ preferences or the similarities with other users [15], [16].
The process of CB approach can be summarized into the following steps [2], [17],
[18]:
1. Item representation: The information source of the item description is used
to extract the item’s characteristics (i.e. features) to produce the
structured item’s representation.
2. Learning the user profile: A user profile is generated from the previous
user’s behaviors (i.e. explicit and implicit feedback) such as like/dislike
of an item; assign a score to an item (rating) or writing a textual opinion
about an item (comment).
3. Recommendations’ generation: A list of items is recommended to the user by
comparing the item’s features with the user’s profile and the items that are
most likely to be interesting to the user are added to the list (i.e.
top-ranked items).
This type of approach has been implemented in many domains [9] especially in
recommending items that contain textual information such as websites, news, and
articles. It also recommends activities such as travel, tourism, e-commerce, and
TVs [15]. This approach is preferred for moderate-sized items.
Some of the CB approach advantages are:
1. It can give an explanation for recommending specific items (i.e. present the
logic behind their recommendations) through providing a list of content
features. This, in turn, can strengthen the user’s confidence about the RS
that reflects his own preferences [16].
2. Since this approach relies on the content of each item, not the ratings of
other users, it gives several advantages as follows [19]:
* It offers a high level of personalization in the recommendations.
* It is scalable in terms of the number of users.
* It can make recommendations for users with peculiar interests.
* It has high security from malicious item creation and allows users to
prevent viral marketing.
On the other hand, CB approaches have some disadvantages such as:
* The vast size of the items is considered a major problem because when the
recommendation is made, the content of every item has to be examined to
discover items that are most likely relatable to the user’s interest [19].
This task is error-prone and time-consuming [20].
* User profiles are built based on the static characteristics of the items. As
a result, there is a high probability that different users have similar
profiles even if they have various preferences among these items, just
because they commented on the same items [9].
* The over-specialization problem occurs in this type of approaches because
users do not receive diverse or new items because of the restriction in his
profile regarding the description of similar items [20].
* Lack of serendipity. Overspecialization can also cause the issue of
serendipity, whereby users are being recommended with familiar items.
B. COLLABORATIVE FILTERING APPROACH
The collaborative filtering approach (CF) is the most popular technique used in
RSs [21]. It generates the recommendation for a user based on the similarities
among users who have similar preferences/interests to him in the past. This
approach is based on the following hypothesis: people who agreed with a user in
the past will also agree in the future [16]. It identifies the new user-item
association by determining the relationships between users and the
interdependencies between items [21]. It uses the implicit knowledge of a
community of users on used items to identify the relationships of those items to
other users who have not used/seen those items within the community [15]. This
can be represented as a user × items matrix in which each cell represents the
user rating of a particular item.
The first CF framework for RS was developed by Resnick et al. [22] called
GroupLens. It recommends articles to the Netnews clients using the rating
server, named Better Bit Bureaus (BBB) which gathers users’ rating to predict
other user’s scores on articles based on the heuristic model that clients who
agreed to the rating of articles in the past they will probably agree in the
future.
CF can be grouped into two classes memory-based and model-based [9]. The
memory-based CF type is a heuristic algorithm that predicts the item’s rating
based on other users’ ratings, and can be classified into two methods [10]:
user-based and item-based, the former identifies a set of neighbors (i.e.
like-minded users) for a target user using ratings then recommend a set of items
that interest his neighbors. While the latter, recommends items to a target user
that are similar (i.e. has shared features) interests in the items that a user
purchased, viewed or liked before. There are two approaches that are most
frequently used to identify the user/item similarity, the Pearson correlation
approach and cosine-based approach [1].
On the other hand, the model-based CF type [23] predicts user’s rating of unseen
items by developing models using different representative techniques such as the
clustering models, Bayesian networks and Markov decision process. A survey by Su
and Khoshgoftaar [23], provided a comparison between the CF classes as shown in
Table 1.
TABLE 1 Comparison Between CF Classes
CF approaches possess many advantages compared to other approaches, some of the
main advantages are:
* Serendipity where novel and unfamiliar items are recommended.
* Able to recommend more subtle items and can capture more nuances around
items.
* Flexible and suitable for various domains.
* No need to analyze the items’ contents.
Generally, the performance of the CF approach depends on the availability of
sufficient user participation [16]. It performs satisfactorily only when there
is adequate rating information [23]. Depending on the ratings exposed CF
approach to the following issues [21], [24]:
1. Sparsity Problem: One of the major problems that complicate the personalized
item ranking process is data sparsity because items cannot be reliably
linked to users [25], causing a limitation in the recommendation’s
effectiveness and limited coverage of recommendation space [26].
This problem occurs due to the following issues [26], [27]:
* Insufficient or missing information of either the user or item or both in
the dataset during the process of filling the ratings (user-item) matrix.
The complexity of gathering the items’ ratings.
* Expressing user’s preferences about items as a rating is a complicated
process.
2. Cold Start Problem: This problem happens in the case of new users who do not
provide any ratings as yet or new items that have not been rated [28]. It
can be considered as a particular case of the sparsity problem in which most
of the cells of the item-user interaction matrix contain null values [29].
The CF approach is not able to generate accurate recommendations for new
users or items without sufficient existing data on them [24].
3. Scalability: The number of users and items in a system grows rapidly. For
example, the behavior of such a user per day may result in his stored data
reaching the size of TBs in some popular websites [30]. Furthermore, the RS
should respond in less than a second to keep users satisfied and to enable
them to continuously engaged with the RS [30]. As a result, both large-scale
datasets and responding time create a challenge in designing efficient RS
and as a result, it demands colossal computing resources.
4. Rating bias: In the CF approach, recommendations are based on users’
ratings, but these ratings cannot show users’ preferences or their clear
opinion on some criteria which makes it difficult in interpreting these
ratings.
C. KNOWLEDGE-BASED APPROACH
This approach is applied in some cases when both content-based and
collaborative-based approaches cannot work properly because no sufficient
ratings are available for a specific item at hand which affects the
recommendation process [31]. For instance, recommending items that are rarely
purchased like cars, houses and financial services. This approach uses the
user’s knowledge of the item domain to recommend items that will best satisfy
his requirements [32]. The main advantage and strength of this approach are that
no-existence of the early-rater problems and cold start problems. While a
corresponding drawback is that it requires knowledge engineering with all of its
attendant difficulties to understand the item’s domain satisfactorily [33].
D. HYBRID APPROACH
This approach aims to mitigate the weakness of both CF and CB and benefit from
their strengths by integrating two or more recommendation components or
algorithm’s implementations in a single recommendation system to enhance RS
accuracy and gain better performance [2], [34]. When the hybrid approach is
generated through hybridizing two or more algorithms, two major points must be
taken into account [2]: the first is the recommendation models that declare the
required inputs and the determination on which the hybrid recommender will be
based on. The second point is determining the strategy that will be used within
the hybrid recommender [35].
Although hybrid approaches may overcome the limitation of both CB and CF
approaches and enhance the prediction performance, it is expensive to implement,
increases the complexity and needs external information that is mostly
unavailable [23].
E. CONVENTIONAL SINGLE-RATING RECOMMENDATION PROBLEM
The aforementioned conventional approaches mostly rely on a single-criterion
rating for generating predictions. This rating is considered as the overall
satisfaction of a user for the item [2]. In other words, most of the RS
approaches work in a two-dimensional space (Users and Items), and the RS uses
the previous ratings made by a user to predict the utility function for the user
of an item represented as a totally ordered set as R:Users×Items [36]. However,
the overall rating is not enough to gain high-performance recommendations
because the overall rating is only a numeric rating with a specific scale that
cannot express a fine-grained analysis about the underlying rationale behind the
users’ rating. It expresses the coarse-grained rating only (i.e. overall rating
cannot reflect the details of user preferences or interest toward each part of
the item to understand users’ opinions and analyze users’ behaviors) [8], [37],
[38].
For example, when a user gives a high rating about an item, it does not mean
that the user likes the item as a whole. There is still a probability that he
dislikes some specific features (i.e. aspects) of that item. Likewise, a low
rating does not imply that the user dislikes everything about the item.
Additionally, when the user puts the overall ratings, he places various emphases
on various aspects and this has a significant effect on the final decision made
by the user [21].
To overcome the shortage of using a single criterion (or an overall rating) in
RS, multiple-criteria decision analysis is combined with RS to form a
multi-criteria recommender system (MCRS) to develop the overall accuracy and
performance of the RS [8], [36]. Thus, by adopting multi-criteria decision
analysis, an item recommendation process is the decision process, a potential
user is the decision-maker, the item attributes are the criteria and the items
are the decision alternatives [2]. The following section presents a survey of
various approaches used for supporting the multi-criteria recommendation.
SECTION III.
MULTI-CRITERIA RECOMMENDER SYSTEM
Multiple-criteria decision-making or Multiple criteria decision analysis (MCDA)
is a sub-discipline of operations research and management science. It aims to
develop tools and methodologies to construct a convincing and reliable model for
addressing complicated decision problems including multiple criteria goals or
multi-alternatives [8].
The idea of combining MCDA with RS is to recommend items that meet users’
personalized needs. In this case, personalization refers to “the ability to
provide services and content that are tailored to users depending on the
knowledge about their behaviors and preferences” [39]. As such, RSs will be able
to comprehend how the user thinks and why the user likes an item and not only
what the user likes [8].
Both single-criterion RS and MCRS have the same goal which is to identify items
that are suitable and relevant to fit the user’s preferences. The difference
between them is that the MCRS has more detailed information about both the items
and users that can be used to efficiently enhance the recommendation
performance. Generally, the rating function in the MCRS is described as follows:
* R: Users × Items → R0×R1×….×Rk; Where R0 is the overall rating and R1,
R2,…,Rk is the rating values for each singular criterion.
As an illustration, consider a hotel RS meant to recommend a suitable hotel
based on the needs and requirements of the target user. In the conventional
single criteria RS, a user (U) provides one rating (overall rating) for the
hotel (I) that he has visited, denoted R (U, I). Specifically, the RS calculates
the predicted rating of the unvisited hotel based on other users’ ratings that
have similar preferences for the target user. The precise choice of the relevant
users is crucial to gain an accurately predicted rating and high-performance
recommendation. So, if two users (U1) and (U2) have rated their overall
satisfaction of the visited hotel 5 out of 10 as presented in Table 2, they will
be considered as neighbors and the predicted rating of the user (U1) for the
unvisited hotel (H4) is calculated using the ratings of the user (U2) and it
will be 9 out of 10. On the other hand, in a multi-criteria rating, a user
provides ratings for multiple features (i.e. attributes) of an item. For
example, in a hotel RS with four criteria such as room, price, location, and
cleanness, the users will provide ratings for these four criteria.
TABLE 2 Multi-Criteria Hotel Recommender System
Suppose we have three users’ ratings for the four features of the hotel (H2)
plus an overall rating as illustrated in Table 2: U1(7overall, 5room , 5price ,
9location , 9cleaness) , U2(7overall , 9room , 9price , 5location , 5cleaness) ,
and U3(7overall , 6room , 6price , 8location , 8cleaness) . If we recommend
based on a single-criterion rating only, all the three users are considered as
neighbors because all of them has an overall rating of 7 out of 10 for the hotel
H2. Considering the three users as neighbors, despite the difference in their
preferences will affect the accuracy of the recommendation’s performance. While,
in the MCRS, when the choice of neighbors is based on the rating of each item’s
feature, users U1 and U2 are not neighbors because they chose different ratings
for the hotel’s features even if they have a similar overall rating, so the
predicting rating for H4 for U1 will be 5. These additional details of users’
preferences from the item’s features help the RS to recommend more accurate
items and enhance the RS performance in general.
MCRS becomes a significant trend in studying RS and it is successful in gaining
the attention of both the industry and research [11]. The numerous research
prove that by using MCRS, the recommendation’s accuracy outperforms the
single-rating RS [11], [40].
The item’s criteria in MCRS are either explicitly represented or implicitly
represented in the user-generated reviews. The next section will discuss these
two types of item’s criteria.
A. MULTI-CRITERIA RECOMMENDER SYSTEM USING EXPLICIT USER PREFERENCES
In this type, the user gives ratings to each of the item’s features with or
without the rating of the whole item. The user’s preferences are known directly
from the users’ ratings on the items’ features (explicitly stated). As an
example, Figure 2 shows two ratings for two hotels from TripAdvisor; each rating
contains an overall rating and multiple criteria ratings, Hotel A contains 4
features/criteria (location, cleanliness, service, and value) while hotel B
contains six features (cleanliness, dining, facilities, location, rooms, and
service).
FIGURE 2.
Example of hotel rating from TripAdvisor.
Show All
A considerable number of research applies this type of MCRS as illustrated in
the works of [1], [8], [40]–[42]. Additionally, there are some researches that
apply MCRS recently and the following are three of them:
* Wasid and Ali [43] proposed a multi-criteria RS using a clustering approach.
The main idea of this approach is to find more similar neighbors of a user
within the user’s cluster in order to improve the recommendation set. To
achieve that, initially the users’ preferences are extracted from the
multi-criteria ratings that they have given for items and the user cluster
centers (C) are defined based on the extracted preferences. Then, the
Euclidean distance is used to assign the closest C for each user and the
Mahalanobis distance is used to compute the top-N neighbors for a user in the
same cluster. After that, the predicting rating of an item for the user is
computed based on similar neighbors who have been chosen from the same
cluster. The approach is evaluated using Yahoo! Movies dataset and the users
who have ratings of at least 20 movies are chosen, yielding to 484 users, 945
movies and 19,050 ratings. An experiment is done to compare the Mean Absolute
Error (MAE) using clustering and without clustering. The result shows that
their clustering method produces the best result with MAE equal to 2.175.
* Zheng [44] developed a utility-based multi-criteria recommender system in
which the items are recommended to a user based on the utility function of
each item for the user. The utility function is built using the
multi-criteria ratings as the similarity between the vector of user
evaluations and the vector of user expectations (i.e. the higher degree of
over-expectations, the higher the similarity between the vectors of the
expectation and the user evaluations). Three similarity measures are used to
calculate the utility score (i.e. Pearson correlation, cosine similarity, and
Euclidean distance). The user expectations are learned by three optimization
learning-to-rank methods (i.e. Pointwise ranking, Pairwise Ranking, and
Listwise Ranking). Evaluation of the proposed method was done using two
datasets which are TripAdvisor and Yahoo! Movies [45]. TripAdvisor contains
of 14,300 hotels, 1502 users (users with at least 10 ratings are chosen), and
22,130 ratings including seven criteria ratings (i.e., price, location,
quality of rooms, cleanliness, convenience of the hotel, service experience
of check-in, and particular business services). While Yahoo! Movies contains
2,162 users who have issued 62,739 ratings on 3,078 movies that have four
criteria (i.e., story, direction, visual effects, and acting). The developed
method is compared with four baselines: the matrix factorization, the linear
aggregation model [40], the hybrid context model [46] and the criteria chain
model [47]. The results outperform the baselines in terms of precision and
NDCG and the Pearson correlation measure gives the best result and the
Listwise ranking gives the most outstanding performance.
* Tallapally et al. [48] used a deep neural network technique called stacked
autoencoders to solve the shortage of single rating RS through using
multi-criteria RS. The conventional stacked autoencoders are extended to fit
with the multi-criteria ratings by adding an extra layer which acts as an
input layer to the autoencoders. The input which is the multiple criteria
ratings is connected to the intermediate layer which is represented by the
items. The intermediate layer is connected to N consecutive encoding layers
where the latent representation for each item is encoded. The last encoding
layer is connected to N consecutive decoding layers. The last layer is the
output layer in which the items’ overall rating is predicted. An experiment
is conducted to evaluate the effectiveness of the proposed network on two
datasets: the TripAdvisor and Yahoo! Movies (YM). For TripAdvisor users who
rated at least five hotels and hotels that have rated by at least five users
are chosen (5-5) leading to 3,550 hotels rated by 3,160 users by 19,374
ratings. Similarly, YM dataset forms three subset YM 5-5, YM 10-10 and YM
20-20. The proposed network result is compared with many baselines such as
[1], [47] and [49]. The result outperforms all the compared baselines in
terms of the following performance metrics MAE, F1, and both Good Items MAE
and Good Predicted Items MAE that was introduced by Cacheda et al. [50].
B. MULTI-CRITERIA RECOMMENDER SYSTEM USING IMPLICIT USER PREFERENCES
In the first type of MCRS, users should give ratings for each feature of the
item regardless of whether he is interested in the features or otherwise. Unlike
this type, users provide opinions only on the item’s feature that they are
interested in through writing comments (i.e. reviews) that express their
feelings or opinions about their experiences with the items. This type of
approach is claimed to be more accurate in determining the users’ preferences
because users will write exclusively about what they concerned with regarding
the items. This, in turn, will enhance the accuracy of the RS, because the more
accurate the user’s preferences are determined, the more accurate the
recommendation provided to the user.
In this type, the criteria of the RS process are implicitly represented and they
need to be extracted from the valuable information of the user-generated
reviews. Figure 3 shows an example of multi-criteria RS where the users’ reviews
are collected from TripAdvisor to extract the hotel’s criteria (i.e. aspects)
such as price, food, location, and bed using sentiment analysis methods. These
aspects are used in building the rating matrix. Then recommend a hotel to a
specific user based on the criteria that are mentioned in his reviews. The
extracted valuable information can be summarized as the review elements. In the
following section, we will explain the reviews, their benefits in RS and the
review elements. Then, we will explore various research that have utilized this
type of MCRS and explain how the review elements enhanced the recommendation
process.
FIGURE 3.
Multi-Criteria RS with Users reviews.
Show All
SECTION IV.
USER-GENERATED REVIEWS
Recently, vast growth in e-commerce and social Websites have been observed and
these Websites encourage users to incorporate their experience with each other.
Therefore, there is a significant number of online comments (i.e. reviews) about
various topics such as hotels, products, movies, restaurants, travel, and
services and they continue to increase on a daily basis [15], [51]. These
reviews are valuable resources for users because they help them in making
decisions before consuming or buying a particular item. Such reviews may provide
an overall overview of the items or specific comments on certain features of the
items [7]. The reviews may also indicate users’ preferences.
Many users are affected by the other customers’ reviews because it is considered
as trustworthy information compared to the vendor’s information [52]. This, in
turn, influences the buying behavior which also helps the vendors and companies
to manage and improve their products and develop new ones based on the users’
preferences which can be extracted from the written reviews [53], [54].
The user’s review exhibits distinct characteristics: it is brief, prone to the
occurrence of noise (i.e., misspelling, many hyperlinks and may include
advertisement), written in the form of plain/textual text without a standard
structure or fixed rules and may contain emoticons. The user writes them just to
explain his usage experience with the item [15], [51]. Due to the previous
characteristics of the reviews, most RS do not use them in generating
recommendations because of the difficulties encountered by the machines to
comprehend written natural language compared to other structured data sources
[25].
A. ANALYSING USER-GENERATED REVIEWS
There are many fields involved in processing textual reviews and extracting the
valuable information from the reviews such as natural language processing, text
mining and opinion mining (or sentiment analysis). In this survey, we are more
interested in the involvement of sentiment analysis with RS because the
sentiment analysis field will help us in determining the user’s preferences by
analyzing the user’s sentiment behind his reviews. Sentiment analysis is a
discipline derived from artificial intelligence, information retrieval, and
natural language processing. It focuses on predicting the positive or negative
polarity of the given entity. Sentiment analysis usually works in three levels:
document-level, sentence-level, and aspect-level.
Leung et al. [27] is the first researcher who indicated the potential advantages
of integrating sentiment analysis field with the CF approaches to improve the
accuracy of the RS performance through calculating an inferred rating from
users’ reviews when the explicit rating is not available. He developed a rating
inference framework that consists of two parts; the first part is a rating
inference which is responsible for calculating the inferred rating from user’s
reviews through extracting the opinion words (OWs) from the reviews and
aggregating the sentiment polarity of such OWs to determine an inferred rating.
While the second part is the recommendation process using the CF approach which
recommends items to users based on the calculated inferred rating. An experiment
is done to infer users’ ratings using the MovieLens-100k dataset which contains
1477 movies, 1065 users (i.e. users with more than 10 reviews) and 30,000
reviews (i.e. reviews with user-specified ratings). The work of Leung et al.
[27] is considered as a hypothesis because there is no evaluation for the RS
performance after the inferred rating is calculated.
After Leung et al. [27], Aciar et al. [16] made the first attempt to use the
user reviews in building RS through developing an ontology to convert the review
content into a structured form that is used to provide recommendations. The
ontology model is built manually with two main components of opinion qualities,
which show the user’s expertise regarding the product; and the product quality,
which indicates the rating that the user made for the product features. Each
review is considered as an ontology instance and it is automatically mapped onto
the ontology through the mapping process. After all the reviews are mapped onto
the ontology, the product’s overall assessment (OA) score (i.e. the final score
for the product based on each product feature’s estimation) is determined
through performing a set of computations. Using OA, this application gives a
recommendation to the user about the product that has the highest OA based on
the features that are mentioned in the user’s request. For the application
evaluation, the authors have yet to do an empirical test for measuring the
performance of the proposed RS. The authors claim that their application
overcomes the cold start problem in the CF techniques. It is beyond the scope of
this paper to discuss various research that exploit users reviews in providing
recommendations. Interested readers may refer to the review done by Adomavicius
and Tuzhilin [10].
B. ADVANTAGES OF USING USER-GENERATED REVIEWS IN RECOMMENDER SYSTEMS
Although there are some difficulties in processing users’ reviews, there are
major advantages that RS can get benefit from them to enhance its performance
especially the reviews that can be broadly accessed over the internet. The
following are some of the reviews’ advantages [37], [55], [56]:
1. Alleviate the data sparsity problem in the case of missing ratings. Reviews
provide valuable and natural information about the user’s interests which
can be extracted and inferred.
2. Relieve cold start problem either for a new user or a new item. It can be
considered as a special instance of the sparsity problem. There are three
cases for causing this problem: the first is a user who enters the system
for the first time (totally new), the second is a user who has not made many
ratings (limited experience) and the third is a user with incomplete (i.e.
partial) preferences. Similarly, for new items either totally new items are
added to the system or items have no ratings. Reviews can solve this type of
problem by providing information that is used to improve recommendation such
as the work of Wang et al. [57].
3. In the case of dense data, the reviews still provide a valuable and detailed
information that can be used to enhance the recommendation accuracy such as:
check the rating quality (compared both the user’s star rating with the
inferred rating from the review’s text, or from review’s helpfulness),
derive users’ aspects or context-dependent-aspect or context-
independent-aspect preferences.
4. The reviews provide rich and useful information in some domains like tourism
and travel, where it is difficult to express user’s preferences as scalar
ratings or collect numerical ratings for items.
5. Reviews help to construct both the user model and item model precisely
because they contain much finer-grained sentiment trend for various features
of a single item.
C. REVIEW ELEMENTS
After agreeing on the review’s usefulness on improving the RS performance, we
can summarize the rich and valuable information (called elements) that can be
extracted from the users’ reviews as follows:
1. Total Review of Polarity Score
A user’s overall opinion can be inferred from his written review about an
item whether he or she likes it or not (positive or negative sentiment),
this overall sentiment can be converted into implicit ratings. Implicit
rating (also called virtual rating) is generated by aggregating the opinion
words of the review (i.e. mostly the adjectives or adverb) and then
calculating the sentiment polarity of each opinion word. For example, the
opinion words in the review in Figure 4 are newly, strategic, friendly,
helpful, spacious, nice, clean, tidy and thumbs up. The total review
polarity score is the summation of all the polarities of the extracted
opinion words, which is done using either machine learning methods or text
mining methods. There is an implicit relationship between the user’s rating
and his expressed comment [15]. As a result, the implicit rating takes the
role of the explicit rating (also called the actual rating) in case the
explicit rating is not available such as in [58]. Additionally, in the case
where the explicit rating is available, the implicit rating can be used
either to enhance the actual rating [59] or be used for both ratings to
enhance the performance of RSs further as illustrated in [21], [60].
2. Review Terms
Review terms are the words that are frequently used or that occurred in the
reviews and extracting them is the easiest way for analyzing users’ reviews.
For example, the terms in the review in Figure 4 are hotel, location, staff,
room, and budget. The Term Frequency-Inverse Document Frequency (TF-IDF),
weight scheme is the most widely used statistical method for measuring the
importance of terms. In this case, the items that are recommended to a user
are based on his term-based profile. Researches that use this type of
element prove its usefulness in improving the RS performance such as in
[20], [61].
3. Review Feature/Aspect/Topic
Review aspect can be defined as a concept that depicts a topic of each
item’s domain and it is restricted to exist in every item; each aspect
consists of a set of words (terms) (e.g., the following terms “attitude,
service, waitress, waiter” correspond to the “Service” aspect). Aspects
comprise of either noun or noun phrases that are common in the domain being
analyzed and must be in every item. In contrast, the terms consist of nouns
that most frequently occur in the reviews and it is not necessary that every
term present themselves in all the items set [7]. Some researchers use the
terminology of feature for aspect such as [62], [63], while others use topic
such as [25] and all the terminologies (aspect, feature, and topic) have the
same meaning. The identification of aspects is usually based on two
approaches: heuristic-based and model-based [64]. The former approach
identifies a set of manually-selected keywords (fix aspects) and then
searches for other related terms by applying the clustering method [65] and
relying on the calculation of the relationship between the aspect and the
candidate’s terms [66], [67]. While in the latter approach, the aspects are
automatically extracted (denoted as learned aspect) and the most popular
model that is applied is Latent Dirichlet Allocation (LDA) [68]. A
comparison between the fix and learned aspects will be discussed in detail
later. The review as a whole gives a coarse-grained opinion about the user’s
preferences, while the review-aspect gives a fine-grained opinion about the
user’s preferences. An aspect-based recommendation is claimed to enhance the
performance of RSs due to its ability in determining the specific
preferences of the user [9], [38], [69]. Besides the advantage of
aspect-extraction in enhancing the accuracy of the RS, one point must be
taken into consideration, which is the number of the extracted aspects,
because the high number of the candidate aspects will negatively affect the
RS’s performance and lead to more sparse data. As a result, aspect selection
is of importance that may influence the performance of the RSs [7]. In the
example illustrated in Figure 4, three aspects have occurred which are
location, staff, and room.
4. Review Context
Review context is the circumstance within which a user expresses his opinion
about the item or some feature of the item. For example, in Figure 4 the
context is traveling for business. Like aspects, review contexts are either
pre-defined (fixed) contexts or learned contexts that are automatically
extracted. It can be discovered through rule-based reasoning, keyword
matching or using a classifier such as LDA-based classifier [9]. The review
context proves its benefit in enhancing the recommendation performance by
either combining it with the explicit rating to predict the user rating for
an item in a specific context [64] or using it in the user modeling as
proposed by Chen and Chen [70] through using context-dependent aspect
preferences or context-independent aspect preferences.
5. Review Comparative Words
A user sometimes writes his opinion about an item by comparing it with other
items in terms of some specific features. This type of element called
comparative opinion where it identifies if item A is superior or inferior to
item B in some shared aspect. The comparative words can be extracted either
using graph relations or a set of linguistic rules and then use them in RSs
in order to enhance the items’ ranking quality such as in [55], [71], [72].
In the review illustrated in Figure 4, ‘best’ is a comparative word used to
emphasize that the price of the hotel is the best compared to others.
6. Review Emoticons
When a user writes a review, he can reflect his mood using some symbolic
representations of icons (faces) (e.g., smile, joy, sadness, distress
faces). Most of the reviews contain icons, (41% of the reviews contain
emoticons [73]), which make them available for use in the recommendation
process in spite of the fact that it is harder to detect them compared to
other review elements. Using these icons, we can infer if the user likes the
item or not (overall rating) and then use this information for better item
recommendation for the users as seen in [74]. Additionally, these icons can
be aggregated with other review elements to enhance the RS performance such
as in [73].
7. Review Helpfulness
For every user’s review, readers can vote by clicking the helpful button for
the review if they find it useful for them. These votes can be used in the
RS to make a better predictions, especially for determining the rating’s
quality score such as in [37], [75]. In other words, the more votes were
given for a review, the more the rating’s quality score is assigned. For
example in Figure 4, the review helpfulness is equal to two which means that
two users get to benefit from this review.
FIGURE 4.
Example of review elements.
Show All
D. ASPECTS TYPE
As mentioned in the previous section, there are two types of aspects, fix
aspects and learned aspects. In the fix aspects type, experts define a fixed set
of aspects manually such as food, price, atmosphere, and service for a
restaurant domain. While in the learned aspects type, some methods are used to
extract the aspects automatically from the users’ reviews. Additionally, some
researchers identity fix aspects at the beginning of their methods then search
for other learned aspects that are related to the fixed aspects from the users’
reviews such as in [63], [76]. Most of the researchers claim that the learned
aspects give better recommendations compared to the fixed aspects [60], [69],
[77].
Learned aspects are preferred than the fixed aspects due to the following
reasons:
1. The number of fixed features (catalog features) are few. This, in turn, will
restrict the range of estimating inter-item similarity at the recommendation
time.
2. The static features in some domains are technical in nature; as a result, it
is hard to know the significance of the feature similarities in practical
terms. For example, a camera item in the product domain has the following
features (resolution, sensor-type, and price) while picture quality and
beautiful design are learned aspects that provide more details about the
camera and make the item’s similarity easier to find.
3. Learned aspects from the user’s review show the user’s preferences are more
accurate compared to the static ones because the user will write in his
reviews only the aspects that he or she is interested in which will make
knowing user’s preferences easier and more obvious.
4. Approaches that use static aspects sometimes fail to provide compatible
recommendations about the user’s preferences. For example, service and food
are both fixed aspects for a specific restaurant, the user put a 5/5 rating
for the restaurant’s service and 2/5 for the food. When the RS gives a
recommendation to this user, it will recommend restaurants that have a good
service but in fact, the user does not care about the restaurant’s service
aspect and care only with the restaurant’s food. Thus, the system is unable
to propose a suitable recommendation for the user.
5. A high number of item’s features produce better results in the
recommendation scenarios because the item is much better described compared
to using fixed features which are typically small in numbers.
SECTION V.
MULTI-CRITERIA REVIEW-BASED RECOMMENDATION APPROACH
Multi-criteria review-based RS uses user reviews to extract the criteria that
will be used in the recommendation process. These criteria are defined from the
review elements explained in the previous section. These criteria can be used on
their own or by combining with the actual users’ ratings. The full cycle
(stages) of the multi-criteria review-based RSs is summarized in Figure 5.
FIGURE 5.
The full cycle of the multi-criteria review-based RSs.
Show All
Multi-criteria review based RS is applied by many kinds of research; each
research has an idea about combining the elements of the user-generated review
with the RS; some use just one review element while others combine more than one
review element. Stated below are recent researches in multi-criteria
review-based RS which are grouped based on the review elements as discussed in
Section IV.
A. TOTAL REVIEW POLARITY SCORE
A user’s general opinion can be inferred from his written review of an item.
This overall sentiment can be converted into an implicit rating. Most of the
works that use total review mainly involved the sentiment analysis approach
whereby the total review polarity scores are generated by aggregating the score
of all the opinion words in the reviews. However, there exist slight variations
among the approaches that used total review polarity score that is mainly
concerned with the variations of the selected opinion words within the reviews.
Pappas and Popescu-Belis [78] work focuses on addressing the problem of
one-class CF. One-class CF problem referred to the CF approach that deals with
nothing but positive explicit feedbacks.
The issue with the one-class CF problem is the identification of negative
instances. Therefore, this approach extracts sentiment information from textual
reviews, and it is integrated with the nearest neighbor model into a
sentiment-aware nearest-neighbor model (SANN) by mapping the sentiment scores
according to the user’s ratings (likes or favorites). The proposed approach
consists of two steps: firstly, the polarity of the user’s reviews is calculated
using a rule-based classifier [79]. Then the sum of the total polarities of each
sentence is normalized. Secondly, the normal neighborhood model is extended by
proposing a sentiment aware nearest neighbor approach using a mapping function
(MF) to combine the user’s ratings with the user polarities resulted from a
rule-based classifier. Three MF are defined, which are random mapping, fixed
mapping and learned to map. To evaluate their application three real datasets
are used which contain both user ratings and comments, namely Vimeo, TED, and
Flicker, which are popular sources for videos, lectures, and images
respectively. The proposed application is compared with five baseline models
which are Top popular, Nearest Neighbors (NN), Singular Value Decomposition
(SVD), Non-negative Matrix Factorization (NMF), and Sparse Non-negative Matrix
Factorization (SNMF). Three performance measures are calculated which are the
mean average precision (MAP), the mean average recall (MAR) and the mean average
F-measure (MAF) using 5-fold cross-validation. The results show that the
proposed approach outperforms all the baseline models which prove that there is
an inherent relationship between user unary feedback (likes or favorites) and
sentiment expressed in user comments.
García-Cumbreras et al. [15] approach exploits the pessimistic and optimistic
behaviors among users of RSs. The idea is to classify users into two classes
(Pessimist and Optimist) according to the average polarity of users’ reviews
then add the user’s class as a new attribute to the CF algorithm. Five
experiments are performed using RapidMiner to prove the effectiveness of the
authors’ idea as follows: the first experiment studies the relation between the
user’s rating and his reviews through calculating the user’s rating from his
reviews using SVM algorithm. The result shows an implicit relation between the
user’s rating and his reviews and it proves that the user’s reviews provide
valuable information that enhances RSs’ performance. While in the second
experiment, the rating prediction is calculated by feeding the rating from the
users’ reviews into the CF using the k Nearest Neighbor (kNN) algorithm for both
user-based and item-based approach. The result of the user-based outperforms
item-based approach. Thus, the authors try to enhance the rating prediction in a
subsequent experiment by adding some characteristics for users by either using a
rating behavior or sentiment analysis of the users’ reviews. In the third
experiment, the rating prediction is calculated using a new attribute called
user classification. The classification is performed based on the average of all
the movie ratings given by each user, whereby the pessimist class is for users
with average ratings < 4 and optimist class is for users with average ratings >
6. The results show that using the user category in rating a prediction based on
the rating only (not reviews) slightly reduce the error prediction values of the
ratings. Finally, the last experiment is similar to the previous one except that
the classification of the users is based on the average polarity of his reviews
and not his ratings. The accuracy of the classification is 80% which proves that
the user can be classified based on reviews only. Additionally, the rating
predicting is calculated in this experiment by feeding the user class into the
CF using kNN, and the results outperform the conventional CF algorithms which
prove that users’ reviews can enhance the RSs’ performance. For performing the
experiments, a new corpus is created from the Internet Movie Database (IMDb)
using an automatic extraction program which retrieves the user rating and
reviews for each movie.
Zhang et al. [73] proposes an algorithm to infer the overall rating (or virtual
rating) from users’ reviews by aggregating the sentiments of the opinion words
with the emoticons that are also included in the reviews to mitigate the
sparsity problem in RSs. The proposed algorithm consists of two main steps: the
first step is a review sentiment classification using SElf-supervised, Lexicon
and Corpus-based (SELC) model to derive the virtual rating, while the second
step is item recommendation using user-based and item-based CF algorithms. The
SELC model combines the unsupervised model with the semi-supervised model.
Through it, the overall sentiment score of each review is calculated from the
two sets which are the sentiment word element set and the emoticons set by
aggregating the scores of the words and emoticons that occur in the target
review. Experiments that compared among user-based, item-based and
non-personalized popularity-based approaches use two datasets: Youku (a Chinese
Website) that does not contain real ratings and Amazon.com (book section) that
has real ratings. The results show that the user-based CF outperforms both the
item-based CF and the non-personalized popularity-based approach in terms of
precision. Experiment on top-N recommendation shows that the user-based CF that
uses both real and virtual ratings performed the best in terms of precision. A
unique feature of this approach is the combination of user textual reviews and
emoticons, which exist in 41% of the users’ reviews.
Table 3 summarizes the main contributions of the recommendation approaches that
exploit total review polarity score elements.
TABLE 3 Summary for Researches That Use Total Review Polarity Score Element
B. REVIEW TERMS
Review terms are the words that frequently occur in a review. The use of review
terms is mainly found in the works of D’Addio et al. [20], [60], and D’Addio and
Manzato [7], [61], which primarily use users’ reviews to produce item
representation that is based on the overall sentiment regarding the items’
features. The approach follows a four-step procedure: text pre-processing,
feature extraction, item representation using sentiment analysis and
recommendation.
The text preprocessing step aims to convert the unstructured user reviews into a
structured form to extract features that can then be used to develop a
vector-based representation for each item. The value of each vector’s position
represents the overall sentiment of a specific feature in all the reviews.
The feature extraction step is the main step and it is quite different from the
four types of research conducted by D’Addio: At the beginning of their approach,
the Transductive Learning for Automatic Term Extraction (TLATE) method proposed
by Conrado et al. [80] is used for extract the features in the works of both
D’Addio et al. [60] and D’Addio and Manzato [61]. Next, they develop two
techniques for feature extraction term-based and aspect-based in the work of
D’Addio and Manzato [7]. For the term-based technique, the candidate features
are extracted if they are tagged as a singular or plural noun and their
frequencies exceed the threshold value. While in the aspect-based technique the
features are extracted after the process of stemming using porter algorithm
[81], stop words removal and clustering. In the last work of D’Addio and Manzato
[61], the feature extraction is made more precise through extracting terms and
aspects using heuristic and machine learning.
In the item representation using the sentiment analysis step, the item vector is
generated using the extracted feature as used in the previous step in which each
position of the item vector is the score of a feature. The score is calculated
using the Stanford CoreNLP proposed by Socher et al. [82]. In the work of
D’Addio and Manzato [61], the score is calculated based on the feature
popularity of all the users.
The last step is the recommendation step where item neighborhood-based CF is
used. The produced items’ vectors are used to discover the items’ similarities
instead of the items’ rating vector and they are then fed into the item
neighborhood-based CF model, and the items with the highest rating are
recommended to the user.
An experiment is conducted to evaluate the proposed approach for each work; for
the works of both D’Addio et al. [20] and D’Addio and Manzato [61], two
databases are combined which are the MovieLens dataset and the Internet Movie
Database (IMDb). The results show that the proposed approach has a better value
in both prec@10 and MAP performance measures compared to the recommendations
based only on structured metadata. For the work of D’Addio and Manzato [7], the
proposed approach is tested on the MovieLens-100K database (ML-100k). The
results show the term-based technique gives better accuracy compared to the
aspect-based technique and the proposed approach in both techniques outperforms
the baselines (the approaches that use structured metadata) in terms of Root
Mean Square Error (RMSE). Finally, the proposed approach of D’Addio et al. [60]
is tested on two databases which are the MovieLens-100K (ML-100k) and
Movielens-2k (HetRec ML). The results outperform all the results obtained from
the compared traditional structured metadata constructions used as baselines in
term of RMSE. The feature extraction technique based on the terms using machine
learning provides the best results since it gives a large set of features and
this provides more details about the items.
C. REVIEW FEATURE/ASPECT/TOPIC
The review aspect can be defined as a concept that describes a topic for each
item’s domain, and it is restricted to exist in every item. Each aspect consists
of a set of terms. Most approaches under this category employ algorithms for
aspect extraction and subsequently identify terms and opinion words associated
with each aspect. Sentiment analysis is then applied to identify the polarity of
each aspect and scores or ratings that have been allocated to the aspects. Some
of the works under this category are as follows.
An approach by Musto et al. [69] follows a two-step process: the first step is
building a framework using a non-symmetric measure called Kullback-Leibler
divergence to extract the aspects, and for each aspect, the sub-aspects are
extracted using phrases and informativeness measures proposed by Tomokiyo and
Hurst [83]. Subsequently, a sentiment score for each main aspect and its
sub-aspects is assigned using two strategies: a model-based algorithm that
utilizes deep learning method proposed by Socher et al. [82] and a lexicon-based
algorithm proposed by Musto et al. [84] which is based on the AFINN wordlist
created by Nielsen [85]. The second step used the extracted aspects to feed the
multi-criteria user-based and item-based CF algorithms. The sentiment score that
resulted from the first step is considered as a rating, and the similarity
between two users (or items) is calculated using the multi-dimensional Euclidean
distance [40]. Their experimental evaluation included three datasets Yelp,
TripAdvisor and Amazon. The best performance is achieved from the user-based CF
with 10 aspects except for the Amazon dataset with 50 aspects. The results of
the proposed algorithm also outperform all the single-criterion recommendation
algorithms and algorithms that are based on the matrix factorization in terms of
mean average error (MAE).
Akhtar et al. [86] present a technique for analyzing hotel reviews and
extracting valuable information from them to help service providers and
customers. The technique is targeted at TripAdvisor website’s users. Two types
of information are crawled and extracted from the TripAdvisor: the review text
and the metadata. Then, each review is classified into one of the predefined
categories. These categories are aspects that frequently recur in the review
data set. After that, the topic modeling technique Latent Dirichlet Allocation
(LDA) is applied to reveal the hidden topics from the reviews. Finally,
sentiment analysis is performed using SentiWordNet corpus to calculate the
review’s polarity by aggregating the positive and negative words in the review.
The experiment is carried out for the Orchid Residency Hotel and 78 reviews are
crawled. After implementing all the previous processes on the reviews, a summary
for the reviews is given showing the most positive, negative and neutral
reviews. However, no evaluation result is reported.
Bauman et al. [87] develop a recommendation method that recommends to a user the
items with the most valuable aspects to enhance the user’s experience with those
items. The valuable aspects are identified using Sentiment Utility Logistic
Model method which consists of two parts, the first part is used for extracting
aspect-sentiment pairs using opinion parser called double propagation proposed
by Qiu et al. [88] for extracting aspects from user reviews and a sentiment
lexicon created by Liu [89] to classify the aspect sentiment (i.e., positive,
negative or neutral). The second part is used for predicting the overall rating
of a review by combining all the sentiment values for all the extracted aspects
in the user’s review and identifies the influence of each aspect on the overall
rating. After the aspect is identified and the overall ratings are estimated,
users’ and items’ profiles are created and the recommendation process is
completed as a classification problem (i.e., the rating is classified as ’like’
if the estimated overall rating is 4 or 5, and ’dislike’ for 1, 2 or 3). An
experiment is done to evaluate the performance of the developed method on the
Yelp dataset for the domains of a restaurant, hotel and beauty, and spa. The
number of the extracted aspects for the three domains are 69, 42 and 45
respectively. The proposed method is compared with three baseline approaches as
follows: the popular aspect approach, the most positive aspect approach and the
most negative aspect approach. The results show the proposed method outperforms
the baseline approaches in terms of the Precision@3 and Area Under Curve (AUC)
[12].
Yang et al. [21] also proposed a similar approach whereby the technique consists
of three main components, opinion mining, aspect weight computing, and overall
rating inference. The opinion mining component is responsible for extracting the
aspects and opinion words from users’ reviews then it computes a rating for each
extracted aspect. The aspect extraction is done using the double propagation
method [88] which selects the relationship between the aspect terms and the
opinion word of type Direct Dependency relationship described using dependency
grammar created by Tesnière [90]. The aspect weight computing component uses a
tensor factorization approach to compute the aspect weight which expresses the
user’s satisfaction about the aspect. The third component is the overall rating
inference which uses the aspect rating (user opinion) of component one and
aspect weight (user preferences) of component two to predict the overall rating
for the item that is not rated by a user. Two datasets are used for the
experiment evaluation which are the movies dataset collected from IMDb website
and hotel dataset provided by Wang et al. [66] in which the user review is
associated with a rating on seven fixed aspects. Two accuracy metrics MAE and
RMSE are computed, and then the results are compared with two baseline models
(MF that does not consider any text reviews and TF that extracts user’s opinions
not only aspects weights). The proposed framework’s results outperform the
baseline models with high accuracy for both datasets.
Dong et al. [77] develop an approach for CB that combines feature similarity and
feature sentiment to recommend items with high priority that are similar and
better than the items in the user’s query. The approach consists of three steps,
and the first step is extracting the product’s features from user-generated
reviews using shallow NLP and statistical methods proposed by Hu and Liu [91]
and Justeson and Katz [92] respectively. The second step is identifying an
opinion for each extracted feature using the opinion pattern method proposed by
Moghaddam and Ester [93]. The third step is generating recommendations for the
user depending on his query Q. This approach recommends items that are not only
similar to Q but also have higher relative sentiment improvement by calculating
the product’s score. The top-N products with the highest score are recommended
to the user. To evaluate the developed approach, data from Amazon.com is
extracted for six product domains such as Phones, Tablets, and GPS, in which
each product has at least ten reviews. Two measure qualities are used which are
rating benefit metric and query product similarity. The former compares two sets
of recommendations depending on their ratings, while the latter computes the
average similarity between the query product and the given recommendations based
on the extracted feature. The experiment results demonstrate significant
benefits in the quality of the given recommendations of the developed approach
compared to Amazon’s recommendations.
Wang et al. [57] focus on solving new users’ problems with partial preferences.
New users usually relate to the cold start problem in RS. Thus, most RS will ask
users to indicate their preferences in some aspects or attributes of the items.
However, such preferences are usually incomplete due to the user’s knowledge gap
of the items. Thus, Wang et al. [57] use users’ reviews at the aspect opinion
levels of the items to predict the missing preferences. The approach extracts
the feature opinions from users’ reviews and maps it to the static item’s
attributes to predict the user’s incomplete preferences [63], [65]. The
sentiment polarity of each opinionated feature is calculated using SentiWordNet
[94], and this is subsequently mapped to the static items’ attributes.
Incomplete preferences of the new users are then inferred by calculating the
similarities between the new user and the like-minded reviewers’ preferences.
The recommendation is based on the new user’s preferences for the top-N items.
The proposed approach is evaluated on a dataset collected from Amazon,
containing 57 users (full preferences are determined), 64 products (digital
cameras), each product has eight static attributes and 4904 reviews. To simulate
the missing preferences of a new user, the partial preferences are selected at
random (i.e., 2, 4, or 6 of his attribute preferences). The proposed approach
achieves better recommendations accuracy compared to the four baselines used
during evaluations: random, PopRank, PartialRank, and HybridRank.
Musat et al. [25] develop a method called topic profile collaborative filtering
(TPCF) to address the problems of data sparsity and non-personalized ranking
methods. TPCF works as follows: a frequency-based technique is utilized to
extract the topics and this is followed by grouping them based on their synonyms
using Wordnet synsets. Then, for each extracted topic, the relevant opinion word
and its polarity are identified through constructing a set of relations such as
the work of DeMarneffe et al. [95] and using the OpinionFinder proposed by
Wilson et al. [96]. Finally, based on the extracted topics and the scores
generated from the polarities of the opinion words, the profile of the user
topic is created. To recommend a product to the user, a product’s score is
calculated using the generated user profile, and the highest product’s score is
recommended to the user. The method is evaluated using a dataset collected from
the TripAdvisor’s website and its result outperforms the baseline method; the
non-personalized product ranking method in terms of MAE and Kendall’s tau rank
correlation coefficient [97]
The work of Chen and Chen [70] attempts to address the issue of context in order
to enhance personalized recommendation. They suggest that people may possess
distinct aspect-level preferences in various contexts. An algorithm for
contextual recommendation by extracting the relationship between the weight of
each user’s preferences and the related context is proposed. Both user’s
preferences and contextual information are extracted from the user’s reviews.
Two types of preferences are detected from the user’s reviews,
context-independent preference, and context-dependent preference. Both
preferences are then combined to generate accurate recommendations. The former
preferences are not affected by context and reflect the individual user’s
requirements for items that do not change over time. It is learned from the
user’s overall ratings and aspect opinions. The latter refers to the
aspect-level requirement under certain context for a user. Contextual opinions
are extracted using a rule-based approach and keyword matching. They experiment
with mutual information, chi-square statistics, and information gain measures
when assigning weights for various aspects in different contexts. Finally, both
context-independent and dependent preferences are combined to compute an item’s
matching score, and the highest top-N scores are recommended to the user. The
proposed algorithm has been tested on two datasets, TripAdvisor and Yelp which
are restaurant datasets. They compare their algorithm with some baseline methods
such as Context Freer and Context Pre-filter; the result of the proposed
algorithm outperforms all the compared methods in terms of the Hit Ratio and
Mean Reciprocal Rank. Additionally, the chi-square statistic method generates
the best results compared to the other two contextual weighting methods.
Jamroonsilp and Prompoon [55] present an approach for item ranking based on the
analysis of the user’s reviews. Five pre-defined aspects for software items are
defined, and the software ranking is calculated by analyzing the users’
comparative sentences from the user’s reviews for each software aspect. It
consists of three phases, gathering user reviews, analyzing the gathered reviews
and calculating software ranking. In the first phase, users’ reviews are
collected from google custom search API for three software topics which include
database management system, PHP web application framework, and content
management system. While in the second phase, the quality term (aspect)
mentioned in the user’s review is classified as one of the five pre-defined
aspects based on the classes given by Coallier [98] and Mairiza et al. [99]; in
addition a score for the quality term is assigned using the lexicon created by
Hu and Liu [91]. This is followed by the extraction of the comparative relation,
and a polarity score is assigned for the relation of the two types of software
and the compared quality term mentioned in the user’s reviews. Finally, in the
third phase, the overall software score is calculated based on all the quality
aspects scores and the relation’s score that are calculated in the previous
phase. The approach is evaluated using the dataset that is collected in the
first phase using Pearson’s correlation coefficient and compared with a human
expert and the work of Zhang et al. [71]. It achieves a high Pearson’s
correlation coefficient with value 0.935 which proves that the software ranking
is statistically consistent with the human experts’ rankings and better than
Zhang’s approach.
Zhang et al. [37] propose an approach that exploits the aspect-level sentiment
of the users’ reviews with the support of helpfulness reviews. The approach
consists of four phases. The first phase is extracting aspects using a latent
Dirichlet allocation model and the words with the highest conditional
probability are chosen as aspects. The second phase is determining the sentiment
orientation of each extracted aspect using the sentiment lexicon SentiWordNet.
By using the extracted aspects and their sentiment orientation, the item model
and user model are created in Phase 3. The item model is represented as a vector
with the mentioned aspects that appear in the product’s reviews with the support
of the helpfulness reviews to give weight to the related aspects. The user model
is represented as a vector with the aspects that frequently occur in the user’s
reviews. The last phase is the recommendation phase, a score for each user and a
candidate item pair is calculated by multiplying both user’s vector and item
vector, and the items with the top k scores are recommended to the user. An
experiment conducted on Yelp dataset (i.e. restaurant domain) evaluates the
proposed approach. The approach is compared with two baseline methods (CF based
on matrix factorization approach and popularity-based approach), and its result
outperforms the two baseline methods in terms of mean reciprocal rank (MRP).
Table 4 provides a summary of all the approaches previously discussed that use
aspects elements in the review-based recommendation.
TABLE 4 Summary of Researches That Use Feature/Aspect/Topic Element
Following Table 5 that provides a summary of all the 28 surveyed approaches
categorized as multi-criteria review-based recommender system.
TABLE 5 Multi-Criteria Review-Based Recommender Systems
SECTION VI.
DISCUSSION
The current state in RS research is concerned with the inability of such systems
in providing an accurate recommendation to users. One of these inabilities
relates to the systems focusing only on single criterion recommendation. To
enhance the RS performance, there is a need to provide more information about
the users and items and make the decision regarding the recommendation process
based on multi-criteria or multi-alternatives that show users’ preferences not
only based on a single-criterion rating. The importance of such multi-criteria
recommender systems is that they build their criteria from the users’ reviews to
enhance the accuracy of the RSs performance and is the primary reason for
conducting this survey.
Relying only on the overall ratings in the recommendation process may result in
inaccurate recommendations because these ratings cannot reflect the users’
preferences accurately. This survey explores how the user-generated reviews can
overcome such problems by utilizing them as an alternative and valuable source
in the recommendation process through merging them with MCRS to define the
recommendation criteria to enhance the accuracy of the RS’s performance.
Additionally, the elements that can be extracted from the user’s reviews are
discussed in detail in this survey, and the recent research by various
researchers who extract the criteria from users’ reviews which have been
discussed and categorized based on the elements used. This is followed by a
table that contains 28 recent studies in the field of multi-criteria
review-based recommender systems. The published papers are collected from
reliable resources such as ACM, Springer, and ScienceDirect and Figure 6
illustrates the statistics of the selected papers by the publisher while Figure
7 illustrates the statistics of the included papers according to the publication
year. All the chosen papers are published in the last 8 years and the reference
Aciar et al. [16] is added because their research is the first attempt to use
user reviews in building RS.
FIGURE 6.
Statistics of the surveyed papers according to publishers.
Show All
FIGURE 7.
Percentage of the surveyed papers by publication year.
Show All
Additionally, the included papers have been cited by others which make them more
reliable. Figure 8 shows the citation number for each reference collected from
the Google Scholar.
FIGURE 8.
Number of citations for each reference included in table 5.
Show All
Follows are some analyzing points that summarize Table 5:
* RS approach
Most of the research that used multi-criteria review-based RS type applied the
CF approach because finding the user’s preferences is the major reason for using
this type of RS and users’ reviews are considered valuable resources for
establishing user preferences’ criteria. On the other hand, CB does not use
users’ details which makes it less preferable compared to this type. So, CF is
the most suitable approach for multi-criteria review-based RS type.
* Review Analysis Method
As mentioned previously, this review is focused on the sentiment analysis method
for review processing. Based on Table 5 it is clear most of the researches
utilize the statistical methods for analyzing the user reviews and extracting
their elements. One of the reasons for using the statistical methods is there
are no labeled datasets that suit the sentiment analysis processing.
Multicriteria review-based RS deals with a considerable number of reviews and it
is a challenging task to label a huge number of reviews and determine the
sentiment words for each review.
* Sentiment Lexicons
Most of the researchers use existing lexicons, and the most prominent two are
the SentiWordNet and StanfordCoreNLP sentiment analysis tools. Accurately
assigning sentiment polarity for each sentiment word is a difficult task and it
is also significantly sensitive depending on the domains. Unfortunately, most of
the lexicons are general and they are domain-independent lexicons. Thus, it may
affect the accuracy of the sentiment analysis process. The work by Wang [6],
however, used a domain-specific lexicon (movie domain) which is built based on
his movie dataset and it shows high precision results compared to others.
* Review Elements
Surprisingly, only a few researchers have used more than one element but the
most are only two. In spite of that, the research that implements two elements
has enhanced the RS performance. Most of the approaches focus on aspect review
element either the fixed or learned aspects. It can be deduced that extracting
the aspects provides more information about the users. This will accordingly
improve the process of recommending items to the users based on their
preferences.
* Rating Type
We can observe that most of the researches use implicit ratings with the view
that implicit ratings deliver more legitimate opinions of the users instead of
the explicit ratings.
* Profile Type
The use of profile types largely depends on the type of RSs. The CF recommender
systems mainly require a rating matrix, whereas the CB recommender systems
exploit the user and item profiles. However, the distinction between these two
types of recommender systems is becoming less crucial as some RSs exploit both
types of profiles.
* Recommendation using the Overall/Preferences rating
Most of the researches obtain benefits from the user reviews element. Thus, they
provide the recommendations based on the overall rating from the elements of the
review or make it more precise based on specific user preferences.
* Evaluation of Data Set
The data sets used for evaluating the RSs are mainly from the Amazon,
TripAdvisor, and Yelp which involve domains such as products, movies, hotels,
and restaurants.
* Performance Measures
There are many measures to evaluate the performance of RS. This is summarized in
Figure 9.
FIGURE 9.
Recommender system performance metrics.
Show All
Error Metric is the performance measure that is used by most of the research
then in comparison with Top-N metrics. Although there is remarkable progress in
multi-criteria review-based recommender systems in recent years, further studies
are needed.
One of the future trends that can be explored is combining various types of
elements of the reviews [9]. Most of the current research works that exploit
user reviews in multi-criteria recommendations only consider one or two elements
as shown in Table 6. All the studies that use two-element combinations from
reviews prove that the accuracy of the RS is enhanced compared to other
baselines. As a result, there is a need for developing multi-criteria RS that
explores more element combinations to improve the accuracy of RS [9].
TABLE 6 Multi-Criteria Review-Based Recommender Systems With the Review Elements
That are Used
Another future trend is precise profiling for users and items from the extracted
elements of the user’s reviews. The recommendation process that generates
recommendations based on user’s preferences makes the RS a tool of
personalization technologies in which the effectiveness of such technologies is
based on the accuracy and completeness of the user’s profiles [8]. As a result,
precise profiling for the user and items is important to gain accurate
recommendations. Despite that, there is a lack of studies that aim to use and
organize the review elements to develop or enhance user and item profiles [7].
Most of the available studies aim to use the “total review polarity score”
element such as [78], [15] or use aspect (i.e. a single element) to develop user
profile or/and item profile such as [38], [60], [87]. As a result, there is a
need to use a combination of the review elements to develop both item and user
profiles to enhance the accuracy of the recommendation performance.
Another point of the forthcoming trends is enhancing the evaluation process of
the existing multi-criteria review-based RSs because it includes some
limitations, especially with the type of baselines that are compared with. For
example, the CB approach that use reviews to build a user’s profile compared
their approach with the profiles that are built from static item description
[56] and not with other profiles that are developed using reviews and the
approaches that use reviews to calculate item rank compared to their approach
with popularity-based approach, not with the approaches that use standard
preferences ranking [9], [55].
Finally, the abundant information gained from the users’ reviews can be used to
produce explanations for users during the recommendation process. This
explanation will increase the user’s trust in using the recommendation system
because it declares and explains why these recommendations are recommended to
him. On the other hand, there is a lack of research that works at this point.
SECTION VII.
CONCLUSION
Currently, user-generated reviews are used to improve the accuracy of the RSs
performance by using text analysis and sentiment analysis to transform the
unstructured user reviews into a structured form that can be merged with RSs.
Many elements can be extracted from the user’s reviews then delivering them to
the RSs approaches to solve the problem of inaccurate recommendations caused by
relying only on the overall ratings in the recommendation process. This survey
concerns the MCRSs that extract their criteria from users’ reviews due to the
apparent improvement implemented to the RSs performance when applying them.
Users’ reviews elements are discussed in detail. The approaches that implement
these elements in the RSs are then explained and grouped based on the review
elements used in developing their systems. After that, the most recent
researches in multi-criteria review based recommender systems are presented in a
table that explained the main points used. Finally, some of the future trends
are discussed as challenges or open problems for this type of RSs.
We expect this survey will help researchers to gain more understanding about the
multi-criteria review based recommender system and encourage them to explore the
implicit values of the reviews and utilize them in future studies.
*
*
*
Authors
Figures
References
Citations
Keywords
Metrics
More Like This
A Framework for Recommender Systems in E-Commerce Based on Distributed Storage
and Data-Mining
2010 International Conference on E-Business and E-Government
Published: 2010
A Literature Review of Data Mining Techniques Used in Collaborative Filtering
Recommender Systems
2020 International Conference on Computational Science and Computational
Intelligence (CSCI)
Published: 2020
Show More
REFERENCES
1.
L. Liu, N. Mehandjiev and D.-L. Xu, "Multi-criteria service recommendation based
on user criteria preferences", Proc. 5th ACM Conf. Recommender Syst., pp. 77-84,
2011.
Show in Context CrossRef Google Scholar
2.
F. Hdioud, B. Frikh and B. Ouhbi, "Multi-criteria recommender systems based on
multi-attribute decision making", Proc. Int. Conf. Inf. Integr. Web-Based Appl.
Services, pp. 203, 2013.
Show in Context CrossRef Google Scholar
3.
A. Ebadi and A. Krzyzak, "A hybrid multi-criteria hotel recommender system using
explicit and implicit feedbacks", Proc. 18th Int. Conf. Appl. Sci. Inf. Syst.
Technol. (ICASIST), pp. 1377-1385, 2016.
Show in Context Google Scholar
4.
N. R. Kermany and S. H. Alizadeh, "A hybrid multi-criteria recommender system
using ontology and neuro-fuzzy techniques", Electron. Commerce Res. Appl., vol.
21, pp. 50-64, Jan./Feb. 2017.
Show in Context CrossRef Google Scholar
5.
F. Peña and R. Riffo, "Revisión selección e implementación de un algoritmo de
recomendación de material bibliográfico utilizando tecnología j2EE", 2008,
[online] Available:
http://repobib.ubiobio.cl/jspui/bitstream/123456789/2394/1/Riffo_Carrillo_Ricardo_Elias.pdf.
Show in Context Google Scholar
6.
Y. Wang, M. Wang and W. Xu, "A sentiment-enhanced hybrid recommender system for
movie recommendation: A big data analytics framework", Wireless Commun. Mobile
Comput., vol. 2018, Mar. 2018.
Show in Context CrossRef Google Scholar
7.
R. M. D’Addio and M. G. Manzato, "A sentiment-based item description approach
for kNN collaborative filtering", Proc. 30th Annu. ACM Symp. Appl. Comput., pp.
1060-1065, 2015.
Show in Context CrossRef Google Scholar
8.
K. Lakiotaki, N. F. Matsatsinis and A. Tsoukias, "Multicriteria user modeling in
recommender systems", IEEE Intell. Syst., vol. 26, pp. 64-76, Mar./Apr. 2011.
Show in Context View Article
Google Scholar
9.
L. Chen, G. Chen and F. Wang, "Recommender systems based on user reviews: The
state of the art", User Model. User-Adapted Interact., vol. 25, pp. 99-154,
2015.
Show in Context CrossRef Google Scholar
10.
G. Adomavicius and A. Tuzhilin, "Toward the next generation of recommender
systems: A survey of the state-of-the-art and possible extensions", IEEE Trans.
Knowl. Data Eng., vol. 17, no. 6, pp. 734-749, Jun. 2005.
Show in Context View Article
Google Scholar
11.
G. Adomavicius, N. Manouselis and Y. Kwon, "Multi-criteria recommender systems"
in Recommender Systems Handbook, Boston, MA, USA:Springer, pp. 769-803, 2011.
Show in Context CrossRef Google Scholar
12.
F. Ricci, L. Rokach and B. Shapira, "Introduction to recommender systems
handbook" in Recommender Systems Handbook, Boston, MA, USA:Springer, pp. 1-35,
2011.
Show in Context CrossRef Google Scholar
13.
G. Adomavicius, R. Sankaranarayanan, S. Sen and A. Tuzhilin, "Incorporating
contextual information in recommender systems using a multidimensional
approach", ACM Trans. Inf. Syst., vol. 23, no. 1, pp. 103-145, 2005.
Show in Context CrossRef Google Scholar
14.
M. Pazzani and D. Billsus, "Learning and revising user profiles: The
identification of interesting Web sites", Mach. Learn., vol. 27, no. 3, pp.
313-331, 1997.
Show in Context CrossRef Google Scholar
15.
M. Á. García-Cumbreras, A. Montejo-Râez and M. C. Díaz-Galiano, "Pessimists and
optimists: Improving collaborative filtering through sentiment analysis", Expert
Syst. Appl., vol. 40, no. 17, pp. 6758-6765, 2013.
Show in Context CrossRef Google Scholar
16.
S. Aciar, D. Zhang, S. Simoff and J. Debenham, "Informed recommender: Basing
recommendations on consumer product reviews", IEEE Intell. Syst., vol. 22, no.
3, pp. 39-47, May/Jun. 2007.
Show in Context View Article
Google Scholar
17.
Y. Blanco-Fernandez, J. J. Pazos-arias, A. Gil-Solla, M. Ramos-Cabrer and M.
Lopez-Nores, "Providing entertainment by content-based filtering and semantic
reasoning in intelligent recommender systems", IEEE Trans. Consum. Electron.,
vol. 54, no. 2, pp. 727-735, May 2008.
Show in Context View Article
Google Scholar
18.
I. Cantador, M. Szomszor, H. Alani, M. Fernández and P. Castells, "Enriching
ontological user profiles with tagging history for multi-domain
recommendations", Proc. CEUR Workshop, pp. 1-16, 2008.
Show in Context Google Scholar
19.
M. J. Pazzani and D. Billsus, "Content-based recommendation systems" in The
Adaptive Web, Berlin, Germany:Springer, pp. 325-341, 2007.
Show in Context CrossRef Google Scholar
20.
R. D’Addio, M. Conrado, S. Resende and M. Manzato, "Generating recommendations
based on robust term extraction from users’ reviews", Proc. 20th Brazilian Symp.
Multimedia Web, pp. 55-58, 2014.
Show in Context CrossRef Google Scholar
21.
C. Yang, X. Yu, Y. Liu, Y. Nie and Y. Wang, "Collaborative filtering with
weighted opinion aspects", Neurocomputing, vol. 210, pp. 185-196, Oct. 2016.
Show in Context CrossRef Google Scholar
22.
P. Resnick, N. Iacovou, M. Suchak, P. Bergstrom and J. Riedl, "GroupLens: An
open architecture for collaborative filtering of netnews", Proc. ACM Conf.
Comput. Supported Cooperat. Work, pp. 175-186, 1994.
Show in Context CrossRef Google Scholar
23.
X. Su and T. M. Khoshgoftaar, "A survey of collaborative filtering techniques",
Adv. Artif. Intell., vol. 2009, Aug. 2009.
Show in Context CrossRef Google Scholar
24.
Y. Chen, C. Wu, M. Xie and X. Guo, "Solving the sparsity problem in recommender
systems using association retrieval", J. Comput., vol. 6, no. 9, pp. 1896-1902,
2011.
Show in Context CrossRef Google Scholar
25.
C. C. Musat, Y. Liang and B. Faltings, "Recommendation using textual opinions",
Proc. Int. Joint Conf. Artif. Intell., pp. 2684-2690, 2013.
Show in Context Google Scholar
26.
S. G. Esparza, M. P. O’Mahony and B. Smyth, "Effective product recommendation
using the real-time Web" in Research and Development in Intelligent Systems
XXVII, London, U.K:Springer, pp. 5-18, 2011.
Show in Context CrossRef Google Scholar
27.
C. W. K. Leung, S. C. F. Chan and F.-L. Chung, "Integrating collaborative
filtering and sentiment analysis: A rating inference approach", Proc. ECAI
Workshop Recommender Syst., pp. 62-66, 2006.
Show in Context Google Scholar
28.
A. I. Schein, A. Popescul, L. H. Ungar and D. M. Pennock, "Methods and metrics
for cold-start recommendations", Proc. 25th Annu. Int. ACM SIGIR Conf. Res.
Develop. Inf. Retr., pp. 253-260, 2002.
Show in Context CrossRef Google Scholar
29.
Z. Huang, H. Chen and D. Zeng, "Applying associative retrieval techniques to
alleviate the sparsity problem in collaborative filtering", ACM Trans. Inf.
Syst., vol. 22, no. 1, pp. 116-142, 2015.
Show in Context CrossRef Google Scholar
30.
Y. Xin, "Challenges in recommender systems: Scalability privacy and structured
recommendations", 2015.
Show in Context Google Scholar
31.
C. C. Aggarwal, Recommender Systems, Cham, Switzerland:Springer, 2016.
Show in Context CrossRef Google Scholar
32.
R. Burke, "Knowledge-based recommender systems" in Encyclopedia of Library and
Information Sciences, New York, NY, USA, vol. 69, pp. 175-186, 2000.
Show in Context Google Scholar
33.
T. Tran, "Combining collaborative filtering and knowledge-based approaches for
better recommendation systems", J. Bus. Technol., vol. 2, no. 2, pp. 17-24,
2007.
Show in Context Google Scholar
34.
V. Danilova and A. Ponomarev, "Hybrid recommender systems: The review of
state-of-the-art research and applications", Proc. 20th Conf. Fruct Assoc.,
2016.
Show in Context Google Scholar
35.
R. Burke, "Hybrid Web recommender systems" in The Adaptive Web, Berlin,
Germany:Springer, pp. 377-408, 2007.
Show in Context CrossRef Google Scholar
36.
A. Caputo, P. Basile, M. de Gemmis, P. Lops, G. Semeraro and G. Rossiello,
"SABRE: A sentiment aspect-based retrieval engine" in Information Filtering and
Retrieval, Cham, Switzerland:Springer, pp. 63-78, 2017.
Show in Context CrossRef Google Scholar
37.
Y. Zhang, R. Liu and A. Li, "A novel approach to recommender system based on
aspect-level sentiment analysis", Proc. 4th Nat. Conf. Electr. Electron. Comput.
Eng. (NCEECE), pp. 1453-1458, 2015.
Show in Context Google Scholar
38.
Z. Cheng, Y. Ding, L. Zhu and M. Kankanhalli, "Aspect-aware latent factor model:
Rating prediction with ratings and reviews", Proc. World Wide Web Conf., pp.
639-648, 2018.
Show in Context CrossRef Google Scholar
39.
G. Adomavicius and A. Tuzhilin, "Personalization technologies: A
process-oriented perspective", Commun. ACM, vol. 48, no. 6, pp. 83-90, 2005.
Show in Context CrossRef Google Scholar
40.
G. Adomavicius and Y. Kwon, "New recommendation techniques for multicriteria
rating systems", IEEE Intell. Syst., vol. 22, no. 3, pp. 48-55, May/Jun. 2007.
Show in Context View Article
Google Scholar
41.
K. Lakiotaki, S. Tsafarakis and N. Matsatsinis, "UTA-Rec: A recommender system
based on multiple criteria analysis", Proc. ACM Conf. Recommender Syst., pp.
219-226, 2008.
Show in Context CrossRef Google Scholar
42.
Y. Zhang, Y. Zhuang, J. Wu and L. Zhang, "Applying probabilistic latent semantic
analysis to multi-criteria recommender system", AI Commun., vol. 22, no. 2, pp.
97-107, 2009.
Show in Context CrossRef Google Scholar
43.
M. Wasid and R. Ali, "An improved recommender system based on multi-criteria
clustering approach", Procedia Comput. Sci., vol. 131, pp. 93-101, Jan. 2018.
Show in Context CrossRef Google Scholar
44.
Y. Zheng, "Utility-based multi-criteria recommender systems", Proc. 34th
ACM/SIGAPP Symp. Appl. Comput., pp. 2529-2531, 2019.
Show in Context CrossRef Google Scholar
45.
D. Jannach, M. Zanker and M. Fuchs, "Leveraging multi-criteria customer feedback
for satisfaction analysis and improved recommendations", Inf. Technol. Tourism,
vol. 14, no. 2, pp. 119-149, 2014.
Show in Context CrossRef Google Scholar
46.
Y. Zheng, "Situation-aware multi-criteria recommender system: Using criteria
preferences as contexts", Proc. Symp. Appl. Comput., pp. 689-692, 2017.
Show in Context CrossRef Google Scholar
47.
Y. Zheng, "Criteria chains: A novel multi-criteria recommendation approach",
Proc. 22nd Int. Conf. Intell. Interfaces, pp. 29-33, 2017.
Show in Context CrossRef Google Scholar
48.
D. Tallapally, R. S. Sreepada, B. K. Patra and K. S. Babu, "User preference
learning in multi-criteria recommendations using stacked auto encoders", Proc.
12th ACM Conf. Recommender Syst, 2018.
Show in Context CrossRef Google Scholar
49.
F. Strub, R. Gaudel and J. Mary, "Hybrid recommender system based on
autoencoders", Proc. 1st Workshop Deep Learn. Recommender Syst., pp. 11-16,
2016.
Show in Context CrossRef Google Scholar
50.
F. Cacheda, V. Carneiro, D. Fernández and V. Formoso, "Comparison of
collaborative filtering algorithms: Limitations of current techniques and
proposals for scalable high-performance recommender systems", ACM Trans. Web,
vol. 5, no. 1, 2011.
Show in Context CrossRef Google Scholar
51.
L. Sun, J. Guo and Y. Zhu, "Applying uncertainty theory into the restaurant
recommender system based on sentiment analysis of online Chinese reviews", World
Wide Web, vol. 22, no. 1, pp. 83-100, 2018.
Show in Context CrossRef Google Scholar
52.
B. Bickart and R. M. Schindler, "Internet forums as influential sources of
consumer information", J. Interact. Marketing, vol. 15, no. 3, pp. 31-40, 2001.
Show in Context CrossRef Google Scholar
53.
E. van Kleef, H. C. M. van Trijp and P. Luning, "Consumer research in the early
stages of new product development: A critical review of methods and techniques",
Food Qual. Preference, vol. 16, no. 3, pp. 181-201, 2005.
Show in Context CrossRef Google Scholar
54.
B. Pang and L. Lee, "Opinion mining and sentiment analysis", Found. Trends Inf.
Retr., vol. 2, no. 1, pp. 1-135, 2008.
Show in Context CrossRef Google Scholar
55.
S. Jamroonsilp and N. Prompoon, "Analyzing software reviews for software
quality-based ranking", Proc. 10th Int. Conf. Elect. Eng./Electron. Comput.
Telecommun. Inf. Technol. (ECTI-CON), pp. 1-6, May 2013.
Show in Context View Article
Google Scholar
56.
S. G. Esparza, M. P. O’Mahony and B. Smyth, "A multi-criteria evaluation of a
user generated content based recommender system", 3rd Workshop Recommender Syst.
Social Web (RSWEB) 5th ACM Conf. Recommender Syst, Oct. 2011.
Show in Context Google Scholar
57.
F. Wang, W. Pan and L. Chen, "Recommendation for new users with partial
preferences by integrating product reviews with static specifications", Proc.
Int. Conf. Modeling Adaptation Pers., pp. 281-288, 2013.
Show in Context CrossRef Google Scholar
58.
D. Poirier, I. Tellier, F. Fessant and J. Schluth, "Towards text-based
recommendations", Proc. Adaptivity Pers. Fusion Heterogeneous Inf., pp. 136-137,
2010.
Show in Context Google Scholar
59.
Š. Pero and T. Horváth, "Opinion-driven matrix factorization for rating
prediction", Proc. Int. Conf. Modeling Adaptation Pers., pp. 1-13, 2013.
Show in Context Google Scholar
60.
R. M. D’Addio, M. A. Domingues and M. G. Manzato, "EExploiting feature
extraction techniques on users’ reviews for movies recommendation", J. Brazilian
Comput. Soc., vol. 23, Jun. 2017.
Show in Context Google Scholar
61.
R. M. D’Addio and M. G. Manzato, "A collaborative filtering approach based on
user’s reviews", Proc. Brazilian Conf. Intell. Syst. (BRACIS), pp. 204-209, Oct.
2014.
Show in Context Google Scholar
62.
R. Dong, M. Schaal, M. P. O’Mahony, K. McCarthy and B. Smyth, "Opinionated
product recommendation", Proc. Int. Conf. Case-Based Reasoning, pp. 44-58, 2013.
Show in Context CrossRef Google Scholar
63.
F. Wang and L. Chen, "Recommendation based on mining product reviewers
preference similarity network", Proc. 6th SNAKDD Workshop, pp. 166, 2012.
Show in Context Google Scholar
64.
G. Chen and L. Chen, "Augmenting service recommender systems by incorporating
contextual opinions from user reviews", User Model. User-Adapted Interact., vol.
25, no. 3, pp. 295-329, 2015.
Show in Context CrossRef Google Scholar
65.
F. Wang and L. Chen, "Recommending inexperienced products via learning from
consumer reviews", Proc. IEEE/WIC/ACM Int. Conf. Web Intell. Intell. Agent
Technol. (WI-IAT), pp. 596-603, Dec. 2012.
Show in Context View Article
Google Scholar
66.
H. Wang, Y. Lu and C. Zhai, "Latent aspect rating analysis on review text data:
A rating regression approach", Proc. 16th ACM SIGKDD Int. Conf. Knowl. Discovery
Data Mining, pp. 783-792, 2010.
Show in Context CrossRef Google Scholar
67.
N. Jakob, S. H. Weber, M. C. Müller and I. Gurevych, "Beyond the stars:
Exploiting free-text user reviews to improve the accuracy of movie
recommendations", Proc. 1st Int. CIKM Workshop Topic-Sentiment Anal. Mass
Opinion, pp. 57-64, 2009.
Show in Context CrossRef Google Scholar
68.
D. M. Blei, A. Y. Ng and M. I. Jordan, "Latent Dirichlet allocation", J. Mach.
Learn. Res., vol. 3, pp. 993-1022, Mar. 2003.
Show in Context Google Scholar
69.
C. Musto, M. de Gemmis, G. Semeraro and P. Lops, "A multi-criteria recommender
system exploiting aspect-based sentiment analysis of users’ reviews", Proc. 11th
ACM Conf. Recommender Syst, 2017.
Show in Context CrossRef Google Scholar
70.
G. Chen and L. Chen, "Recommendation based on contextual opinions", Proc. Int.
Conf. Modeling Adaptation Pers., pp. 61-73, 2014.
Show in Context CrossRef Google Scholar
71.
K. Zhang, R. Narayanan and A. N. Choudhary, "Voice of the customers: Mining
online customer reviews for product feature-based ranking", Proc. WOSN, vol. 10,
pp. 11, 2010.
Show in Context Google Scholar
72.
M. Ganapathibhotla and B. Liu, "Mining opinions in comparative sentences", Proc.
22nd Int. Conf. Comput. Linguistics, vol. 1, pp. 241-248, 2008.
Show in Context CrossRef Google Scholar
73.
W. Zhang, G. Ding, L. Chen, C. Li and C. Zhang, "Generating virtual ratings from
chinese reviews to augment online recommendations", ACM Trans. Intell. Syst.
Technol., vol. 4, no. 1, 2013.
Show in Context CrossRef Google Scholar
74.
Y. Moshfeghi, B. Piwowarski and J. M. Jose, "Handling data sparsity in
collaborative filtering using emotion and semantic based features", Proc. 34th
Int. ACM SIGIR Conf. Res. Develop. Inf. Retr., pp. 625-634, 2011.
Show in Context CrossRef Google Scholar
75.
S. Raghavan, S. Gunasekar and J. Ghosh, "Review quality aware collaborative
filtering", Proc. 6th ACM Conf. Recommender Syst., pp. 123-130, 2012.
Show in Context CrossRef Google Scholar
76.
M. Siering, A. V. Deokar and C. Janze, "Disentangling consumer recommendations:
Explaining and predicting airline recommendations based on online reviews",
Decis. Support Syst., vol. 107, pp. 52-63, Mar. 2018.
Show in Context CrossRef Google Scholar
77.
R. Dong, M. P. O’Mahony, M. Schaal, K. McCarthy and B. Smyth, "Sentimental
product recommendation", Proc. 7th ACM Conf. Recommender Syst., pp. 411-414,
2013.
Show in Context CrossRef Google Scholar
78.
N. Pappas and A. Popescu-Belis, "Adaptive sentiment-aware one-class
collaborative filtering", Expert Syst. Appl., vol. 43, pp. 23-41, Jan. 2016.
Show in Context CrossRef Google Scholar
79.
T. Wilson, J. Wiebe and P. Hoffmann, "Recognizing contextual polarity in
phrase-level sentiment analysis", Proc. Conf. Hum. Lang. Technol. Empirical
Methods Natural Lang. Process, 2005.
Show in Context CrossRef Google Scholar
80.
M. S. Conrado, R. G. Rossi, T. A. S. Pardo and S. O. Rezende, "Applying
transductive learning for automatic term extraction: The case of the ecology
domain", Proc. 2nd Int. Conf. Inform. Appl. (ICIA), pp. 264-269, Sep. 2013.
Show in Context View Article
Google Scholar
81.
H. Schütze, P. Raghavan and C. D. Manning, Introduction to Information
Retrieval, Cambridge, U.K:Cambridge Univ. Press, vol. 39, 2008.
Show in Context Google Scholar
82.
R. Socher, A. Perelygin, J. Wu, J. Chuang, C. D. Manning, A. Ng, et al.,
"Recursive deep models for semantic compositionality over a sentiment treebank",
Proc. Conf. Empirical Methods Natural Lang. Process., pp. 1631-1642, 2013.
Show in Context Google Scholar
83.
T. Tomokiyo and M. Hurst, "A language model approach to keyphrase extraction",
Proc. ACL Workshop Multiword Expressions Anal. Acquisition Treat, vol. 18, 2003.
Show in Context CrossRef Google Scholar
84.
C. Musto, G. Semeraro and M. Polignano, "A comparison of lexicon-based
approaches for sentiment analysis of microblog posts", Proc. DART AI IA, vol.
59, pp. 59-68, 2014.
Show in Context Google Scholar
85.
F. Å. Nielsen, "A new ANEW: Evaluation of a word list for sentiment analysis in
microblogs", arXiv:1103.2903, 2011, [online] Available:
https://arxiv.org/abs/1103.2903.
Show in Context Google Scholar
86.
N. Akhtar, N. Zubair, A. Kumar and T. Ahmad, "Aspect based sentiment oriented
summarization of hotel reviews", Procedia Comput. Sci., vol. 115, pp. 563-571,
Jan. 2017.
Show in Context CrossRef Google Scholar
87.
K. Bauman, B. Liu and A. Tuzhilin, "Aspect based recommendations: Recommending
items with the most valuable aspects based on user reviews", Proc. 23rd ACM
SIGKDD Int. Conf. Knowl. Discovery Data Mining, pp. 717-725, 2017.
Show in Context CrossRef Google Scholar
88.
G. Qiu, B. Liu, J. Bu and C. Chen, "Opinion word expansion and target extraction
through double propagation", Comput. Linguistics, vol. 37, no. 1, pp. 9-27,
2011.
Show in Context CrossRef Google Scholar
89.
B. Liu, Sentiment Analysis: Mining Opinions Sentiments and Emotions, Cambridge,
U.K.:Cambridge Univ. Press, 2015.
Show in Context CrossRef Google Scholar
90.
L. Tesniére, Élements de Syntaxe Structurale, Paris, France:Klincksieck, 1965.
Show in Context Google Scholar
91.
M. Hu and B. Liu, "Mining and summarizing customer reviews", Proc. 10th ACM
SIGKDD Int. Conf. Knowl. Discovery Data Mining, pp. 168-177, 2004.
Show in Context CrossRef Google Scholar
92.
J. S. Justeson and S. M. Katz, "Technical terminology: Some linguistic
properties and an algorithm for identification in text", Natural Lang. Eng.,
vol. 1, no. 1, pp. 9-27, 1995.
Show in Context CrossRef Google Scholar
93.
S. Moghaddam and M. Ester, "Opinion digger: An unsupervised opinion miner from
unstructured product reviews", Proc. 19th ACM Int. Conf. Inf. Knowl. Manage.,
pp. 1825-1828, 2010.
Show in Context CrossRef Google Scholar
94.
A. Esuli and F. Sebastiani, "SentiWordNet: A high-coverage lexical resource for
opinion mining", Evaluation, vol. 17, pp. 1-26, 2007.
Show in Context Google Scholar
95.
M.-C. De Marneffe, B. MacCartney and C. D. Manning, "Generating typed dependency
parses from phrase structure parses", Proc. LREC, pp. 449-454, 2006.
Show in Context Google Scholar
96.
T. Wilson, P. Hoffmann, S. Somasundaran, J. Kessler, J. Wiebe, Y. Choi, et al.,
"OpinionFinder: A system for subjectivity analysis", Proc. HLT/EMNLP Interact.
Demonstrations, pp. 34-35, 2005.
Show in Context CrossRef Google Scholar
97.
M. G. Kendall, "A new measure of rank correlation", Biometrika, vol. 30, pp.
81-93, Jun. 1938.
Show in Context CrossRef Google Scholar
98.
ISO/IEC, 9126-1, "Software Engineering—Product Quality—Part 1: Quality Model",
F. Coallier, 2001.
Show in Context Google Scholar
99.
D. Mairiza, D. Zowghi and N. Nurmuliani, "An investigation into the notion of
non-functional requirements", Proc. ACM Symp. Appl. Comput., pp. 311-317, 2010.
Show in Context CrossRef Google Scholar
100.
D. Rafailidis and F. Crestani, "Adversarial training for review-based
recommendations", Proc. 42nd Int. ACM SIGIR Conf. Res. Develop. Inf. Retr., pp.
1057-1060, 2019.
CrossRef Google Scholar
101.
Z. Cheng, X. Chang, L. Zhu, R. C. Kanjirathinkal and M. Kankanhalli, "MMALFM:
Explainable recommendation by leveraging reviews and images", ACM Trans. Inf.
Syst., vol. 37, no. 2, 2019.
CrossRef Google Scholar
102.
C. Manning, M. Surdeanu, J. Bauer, J. Finkel, S. Bethard and D. McClosky, "The
Stanford CoreNLP natural language processing toolkit", Proc. 52nd Annu. Meeting
Assoc. Comput. Linguistics Syst. Demonstrations, pp. 55-60, 2014.
CrossRef Google Scholar
103.
S. D. Kamvar and J. Harris, "We feel fine and searching the emotional Web",
Proc. 4th ACM Int. Conf. Web Search Data Mining, pp. 117-126, 2011.
CrossRef Google Scholar
104.
P. J. Stone, D. C. Dunphy and M. S. Smith, "The general inquirer: A computer
approach to content analysis", 1966, [online] Available:
http://www.wjh.harvard.edu/inquirer/homecat.htm.
Google Scholar
105.
X. Zheng, Y. Luo, L. Sun, J. Zhang and F. Chen, "A tourism destination
recommender system using users’ sentiment and temporal dynamics", J. Intell.
Inf. Syst., vol. 51, no. 3, pp. 557-578, 2018.
CrossRef Google Scholar
106.
X. L. L. H. P. Yu and R. H. C. Jianmei, "Constructing the affective lexicon
ontology", J. China Soc. Sci. Tech. Inf., vol. 2, pp. 6, 2008.
Google Scholar
IEEE PERSONAL ACCOUNT
* Change username/password
PURCHASE DETAILS
* Payment Options
* View Purchased Documents
PROFILE INFORMATION
* Communications Preferences
* Profession and Education
* Technical interests
NEED HELP?
* US & Canada: +1 800 678 4333
* Worldwide: +1 732 981 0060
* Contact & Support
FOLLOW
*
*
*
About IEEE Xplore | Contact Us | Help | Accessibility | Terms of Use |
Nondiscrimination Policy | IEEE Ethics Reporting | Sitemap | IEEE Privacy Policy
A not-for-profit organization, IEEE is the world's largest technical
professional organization dedicated to advancing technology for the benefit of
humanity.
© Copyright 2023 IEEE - All rights reserved.
IEEE ACCOUNT
* Change Username/Password
* Update Address
PURCHASE DETAILS
* Payment Options
* Order History
* View Purchased Documents
PROFILE INFORMATION
* Communications Preferences
* Profession and Education
* Technical Interests
NEED HELP?
* US & Canada: +1 800 678 4333
* Worldwide: +1 732 981 0060
* Contact & Support
* About IEEE Xplore
* Contact Us
* Help
* Accessibility
* Terms of Use
* Nondiscrimination Policy
* Sitemap
* Privacy & Opting Out of Cookies
A not-for-profit organization, IEEE is the world's largest technical
professional organization dedicated to advancing technology for the benefit of
humanity.
© Copyright 2023 IEEE - All rights reserved. Use of this web site signifies your
agreement to the terms and conditions.