www.tandfonline.com Open in urlscan Pro
2606:4700:4400::ac40:9485  Public Scan

Form analysis
2 forms found in the DOM

Name: quickSearch — GET /action/doSearch

<form action="/action/doSearch" name="quickSearch" class="quickSearchForm " title="Quick Search" role="search" method="get" onsubmit="appendSearchFilters(this)" aria-label="Quick Search"><span class="simpleSearchBoxContainer">
    <input name="AllField" class="searchText main-search-field autocomplete ui-autocomplete-input" value="" type="search" id="searchText-d46e3260-1f5c-4802-821a-28a03a699c82" title="Type search term here" aria-label="Search"
      placeholder="Enter keywords, authors, DOI, etc" autocomplete="off" data-history-items-conf="3" data-publication-titles-conf="3" data-publication-items-conf="3" data-topics-conf="3" data-contributors-conf="3" data-fuzzy-suggester="false"
      data-auto-complete-target="title-auto-complete">
  </span>
  <span class="searchDropDownDivRight">
    <label for="searchInSelector-d46e3260-1f5c-4802-821a-28a03a699c82" class="visuallyhidden">Search in:</label>
    <select id="searchInSelector-d46e3260-1f5c-4802-821a-28a03a699c82" name="SeriesKey" class="js__searchInSelector">
      <option value="rdij20" data-search-in="thisJournal"> This Journal </option>
      <option value="" data-search-in="default"> Anywhere </option>
    </select>
  </span>
  <div class="quick-search-btn">
    <button class="mainSearchButton searchButtons pointer" type="submit" value="" title="Search" aria-label="Search"></button>
  </div>
</form>

Name: frmLogin — POST /action/doLogin

<form action="/action/doLogin" name="frmLogin" class="note denialLogin" method="post"><input type="hidden" name="loginUri" value="/doi/full/10.1080/21670811.2015.1093271">
  <input type="hidden" name="redirectUri" value="/doi/full/10.1080/21670811.2015.1093271">
  <label for="login">
    <span class="off-screen">Username</span>
    <input id="login" class="textInput" type="text" name="login" value="" size="15" placeholder="Enter your email"></label>
  <label for="password">
    <span class="off-screen">Password</span>
    <input id="password" class="textInput" type="password" name="password" value="" autocomplete="off" placeholder="Enter your password"></label>
  <div class="passwordReminder">
    <a href="/action/requestResetPassword?redirectUri=%2Fdoi%2Ffull%2F10.1080%2F21670811.2015.1093271">Forgot password?</a>
  </div>
  <label for="savePassword" class="save-password">
    <input id="savePassword" type="checkbox" name="savePassword" value="1" checked="checked"><span>Keep me logged in (not suitable for shared devices).</span>
  </label>
  <div class="save-password--info"><i>You will otherwise be logged out automatically, after a limited period, and will need to log in again.</i></div>
  <a href="#" class="submit-login">Log in</a>
  <noscript>
    <style>
      .submit-login {
        display: none;
      }
    </style>
    <input class="ecommLoginSigninButton" type="submit" name="submit" value="Log in">
  </noscript>
</form>

Text Content

Skip to Main Content
Log in  |  Register
Cart
 1. Home
 2. All Journals
 3. Digital Journalism
 4. List of Issues
 5. Volume 4, Issue 1
 6. Quantitative analysis of large amounts o ....

Search in: This Journal Anywhere

Advanced search
Digital Journalism Volume 4, 2016 - Issue 1: Rethinking Research Methods in an
Age of Digital Journalism. Guest editors: Michael Karlsson and Helle Sjøvaag
Submit an article Journal homepage

7,341
Views
259
CrossRef citations to date
12
Altmetric
Articles


QUANTITATIVE ANALYSIS OF LARGE AMOUNTS OF JOURNALISTIC TEXTS USING TOPIC
MODELLING

Carina JacobiDepartment of Communication, University of Vienna,
AustriaCorrespondencecarina.jacobi@univie.ac.at

,
Wouter van AtteveldtDepartment of Communication Science, VU University
Amsterdam, The NetherlandsCorrespondencewouter@vanatteveldt.com

&
Kasper WelbersDepartment of Communication Science, VU University Amsterdam, The
NetherlandsCorrespondencek.welbers@vu.nl

Pages 89-106 | Published online: 13 Oct 2015
 * Cite this article
 * https://doi.org/10.1080/21670811.2015.1093271
 * CrossMark


 

 * Full Article
 * Figures & data
 * References
 * Citations
 * Metrics
 * Reprints & Permissions
 * Read this article /doi/full/10.1080/21670811.2015.1093271?needAccess=true


ABSTRACT

The huge collections of news content which have become available through digital
technologies both enable and warrant scientific inquiry, challenging journalism
scholars to analyse unprecedented amounts of texts. We propose Latent Dirichlet
Allocation (LDA) topic modelling as a tool to face this challenge. LDA is a
cutting edge technique for content analysis, designed to automatically organize
large archives of documents based on latent topics, measured as patterns of word
(co-)occurrence. We explain how this technique works, how different choices by
the researcher affect the results and how the results can be meaningfully
interpreted. To demonstrate its usefulness for journalism research, we conducted
a case study of the New York Times coverage of nuclear technology from 1945 to
the present, partially replicating a study by Gamson and Modigliani. This shows
that LDA is a useful tool for analysing trends and patterns in news content in
large digital news archives relatively quickly.

Keywords:

 * automatic content analysis
 * journalism
 * nuclear energy
 * topic models

View correction statement:
Corrigendum



DISCLOSURE STATEMENT

No potential conflict of interest was reported by the authors.


NOTES

1. Factor analysis is a dimensionality reduction technique: given a set of
observed variables, a smaller set of factors is calculated that preserve as much
information as possible in a lower-dimensional space. This is often used in the
field of psychology as a measurement of latent, unobserved causes for certain
observations. For instance, if a single factor largely explains the results for
a set of questions relating to anxiety, the factor can be interpreted as a
measurement of anxiety. Similarly, a topic in topic modelling can be interpreted
and named based on what the main words have in common.

2. Technically, the alpha hyper-parameter controls the concentration of the
Dirichlet distribution regarding the distribution of topics over documents. In
Bayesian statistics, a hyper-parameter is a parameter that controls
distributions such as the Dirichlet distribution. The term hyper-parameter is
used to distinguish them from the parameters of the topic model that is the
result of the analysis. For a good explanation of the role of hyper-parameters,
we suggest the introduction to the Dirichlet distribution by Frigyik, Kapila,
and Gupta (Citation2010).

3. A goodness-of-fit measure describes how similar the predicted or expected
values of a model are to the actual observed values. An example is the R2
measure in linear regression, which indicates what proportion of variance of the
dependent variable is explained by the independent variables.

4. See http://www.r-project.org.

5. See http://amcat.nl.

6. See http://github.com/amcat/amcat-r for the relevant R code. The R scripts
that were used for our analysis can be downloaded from
http://github.com/AUTHOR/corpus-tools.

7. See http://github.com/AUTHOR/xtas for the xtas modules for corenlp and other
lemmatizers.

8. The topic browser can be found at http://rpubs.com/Anonymous/78,706.

9. Our R script for creating a topic browser is available at
http://github.com/vanatteveldt/topicbrowser.






LOG IN VIA YOUR INSTITUTION

Loading institutional login options...

Access through your institution


LOG IN TO TAYLOR & FRANCIS ONLINE

Log in
Shibboleth


LOG IN TO TAYLOR & FRANCIS ONLINE

Username Password
Forgot password?
Keep me logged in (not suitable for shared devices).
You will otherwise be logged out automatically, after a limited period, and will
need to log in again.
Log in



RESTORE CONTENT ACCESS

Restore content access for purchases made as guest
Purchase options * Save for later Item saved, go to cart

PDF download + Online access

 * 48 hours access to article PDF & online version
 * Article PDF can be downloaded
 * Article PDF can be printed

EUR 45.00 Add to cart





PDF download + Online access - Online Checkout

Issue Purchase

 * 30 days online access to complete issue
 * Article PDFs can be downloaded
 * Article PDFs can be printed

EUR 78.00 Add to cart





Issue Purchase - Online Checkout
* Local tax will be added as applicable
 * Share icon
   X Facebook LinkedIn Email Share
   
 * 

 


RELATED RESEARCH

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI
driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.

 * People also read
 * Recommended articles
 * Cited by
   259

Applying LDA Topic Modeling in Communication Research: Toward a Valid and
Reliable Methodology
Daniel Maier et al.
Communication Methods and Measures
Published online: 16 Feb 2018
Topic models meet discourse analysis: a quantitative tool for a qualitative
approach
Thomas Jacobs et al.
International Journal of Social Research Methodology
Published online: 7 Feb 2019
What We Can Do and Cannot Do with Topic Modeling: A Systematic Review
Yingying Chen et al.
Communication Methods and Measures
Published online: 19 Jan 2023
View more




INFORMATION FOR

 * Authors
 * R&D professionals
 * Editors
 * Librarians
 * Societies


OPEN ACCESS

 * Overview
 * Open journals
 * Open Select
 * Dove Medical Press
 * F1000Research


OPPORTUNITIES

 * Reprints and e-prints
 * Advertising solutions
 * Accelerated publication
 * Corporate access solutions


HELP AND INFORMATION

 * Help and contact
 * Newsroom
 * All journals
 * Books


KEEP UP TO DATE

Register to receive personalised research and resources by email
Sign me up
Taylor and Francis Group Facebook page
Taylor and Francis Group X Twitter page
Taylor and Francis Group Linkedin page

Taylor and Francis Group Youtube page
Taylor and Francis Group Weibo page



Copyright © 2024 Informa UK Limited Privacy policy Cookies Terms & conditions
Accessibility

Registered in England & Wales No. 3099067
5 Howick Place | London | SW1P 1WG




YOUR DOWNLOAD IS NOW IN PROGRESS AND YOU MAY CLOSE THIS WINDOW

Did you know that with a free Taylor & Francis Online account you can gain
access to the following benefits?
 * Choose new content alerts to be informed about new research of interest to
   you
 * Easy remote access to your institution's subscriptions on any device, from
   any location
 * Save your searches and schedule alerts to send you new results
 * Export your search results into a .csv file to support your research

Have an account?
Login now Don't have an account?
Register for free




LOGIN OR REGISTER TO ACCESS THIS FEATURE

Have an account?
Login now Don't have an account?
Register for free
Register a free Taylor & Francis Online account today to boost your research and
gain these benefits:
 * Choose new content alerts to be informed about new research of interest to
   you
 * Easy remote access to your institution's subscriptions on any device, from
   any location
 * Save your searches and schedule alerts to send you new results
 * Export your search results into a .csv file to support your research

Register now or learn more

×

View all notes
Cookies Button


ABOUT COOKIES ON THIS SITE

We and our partners use cookies to enhance your website experience, learn how
our site is used, offer personalised features, measure the effectiveness of our
services, and tailor content and ads to your interests while you navigate on the
web or interact with us across devices. You can choose to accept all of these
cookies or only essential cookies. To learn more or manage your preferences,
click “Settings”. For further information about the data we collect from you,
please see our Privacy Policy
Accept All
Settings



COOKIE POLICY

When you visit any website, it may store or retrieve information on your
browser, mostly in the form of cookies. This information might be about you,
your preferences or your device and is mostly used to make the site work as you
expect it to. The information does not usually directly identify you, but it can
give you a more personalized web experience. Because we respect your right to
privacy, you can choose not to allow some types of cookies. Click on the
different category headings to find out more and change our default settings.
However, blocking some types of cookies may impact your experience of the site
and the services we are able to offer.
More information
Allow All


MANAGE CONSENT PREFERENCES

STRICTLY NECESSARY COOKIES

Always Active

These cookies are necessary for the website to function and cannot be switched
off in our systems. They are usually only set in response to actions made by you
which amount to a request for services, such as setting your privacy
preferences, logging in or filling in forms.    You can set your browser to
block or alert you about these cookies, but some parts of the site will not then
work. These cookies do not store any personally identifiable information.

Cookies Details‎

PERFORMANCE COOKIES

Performance Cookies

These cookies allow us to count visits and traffic sources so we can measure and
improve the performance of our site. They help us to know which pages are the
most and least popular and see how visitors move around the site.    All
information these cookies collect is aggregated and therefore anonymous. If you
do not allow these cookies we will not know when you have visited our site, and
will not be able to monitor its performance.

Cookies Details‎

FUNCTIONAL COOKIES

Functional Cookies

These cookies enable the website to provide enhanced functionality and
personalisation. They may be set by us or by third party providers whose
services we have added to our pages.    If you do not allow these cookies then
some or all of these services may not function properly.

Cookies Details‎

TARGETING COOKIES

Targeting Cookies

These cookies may be set through our site by our advertising partners. They may
be used by those companies to build a profile of your interests and show you
relevant adverts on other sites.    They do not store directly personal
information, but are based on uniquely identifying your browser and internet
device. If you do not allow these cookies, you will experience less targeted
advertising.

Cookies Details‎
Back Button


COOKIE LIST



Search Icon
Filter Icon

Clear
checkbox label label
Apply Cancel
Consent Leg.Interest
checkbox label label
checkbox label label
checkbox label label

Confirm My Choices




✓
Thanks for sharing!
AddToAny
More…