Big Social Data Analytics in Journalism and Mass Communication
Journalism & Mass Communication QuarterlyPublished 1 April 2016
Лэй Гуо, Chris J. Vargo, Zixuan Pan, Weicong Ding, Prakash Ishwar
Citations224
SJR quartileQ1
SJR score1.33
SNIP1.69
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This article presents an empirical study that investigated and compared two “big data” text analysis methods: dictionary-based analysis, perhaps the most popular automated analysis approach in social science research, and unsupervised topic modeling (i.e., Latent Dirichlet Allocation [LDA] analysis), one of the most widely used algorithms in the field of computer science and engineering.
Abstract
This article presents an empirical study that investigated and compared two “big data” text analysis methods: dictionary-based analysis, perhaps the most popular automated analysis approach in social science research, and unsupervised topic modeling (i.e., Latent Dirichlet Allocation [LDA] analysis), one of the most widely used algorithms in the field of computer science and engineering. By applying two “big data” methods to make sense of the same dataset—77 million tweets about the 2012 U.S. presidential election—the study provides a starting point for scholars to evaluate the efficacy and validity of different computer-assisted methods for conducting journalism and mass communication research, especially in the area of political communication.
Keywords
Social Sciences
Journal of Machine Learning ResearchLatent dirichlet allocation
27,049 Citations2003David M. Blei, Andrew Y. Ng +1 more
Cambridge University Press eBooksIntroduction to Information Retrieval
10,873 Citations2008Christopher D. Manning, Prabhakar Raghavan +1 more
This textbook teaches classical and web information retrieval, including web search and the related areas of text classification and text clustering from basic concepts, making it perfect for introductory courses in information retrieval for advanced undergraduates and graduate students in computer science.
Software Framework for Topic Modelling with Large Corpora
3,806 Citations2010R Rehr Uv Rek, Petr Sojka
This work describes a Natural Language Processing software framework which is based on the idea of document streaming, i.e. processing corpora document after document, in a memory independent fashion, and implements several popular algorithms for topical inference, including Latent Semantic Analysis and Latent Dirichlet Allocation in a way that makes them completely independent of the training corpus size.
Human Communication ResearchContent Analysis in Mass Communication: Assessment and Reporting of Intercoder Reliability
2,886 Citations2002Matthew Lombard, Jennifer Snyder‐Duch +1 more
A content analysis of 200 studies utilizing content analysis published in the communication literature between 1994 and 1998 is used to characterize practices in the field and demonstrate that mass communication researchers often fail to assess (or at least report) intercoder reliability and often rely on percent agreement, an overly liberal index.
American Journal of Political ScienceIssue Ownership in Presidential Elections, with a 1980 Case Study
2,818 Citations1996John R. Petrocik
Analyzing media messages using quantitative content analysis in research
2,263 Citations2019Daniel Riffe, Stephen Lacy +1 more
Online Learning for Latent Dirichlet Allocation
1,294 Citations2010Matthew D. Hoffman, Francis Bach +1 more
An online variational Bayes (VB) algorithm for Latent Dirichlet Allocation (LDA) based on online stochastic optimization with a natural gradient step is developed, which shows converges to a local optimum of the VB objective function.
Lecture notes in computer scienceComparing Twitter and Traditional Media Using Topic Models
1,206 Citations2011Wayne Xin Zhao, Jing Jiang +5 more
This paper empirically compare the content of Twitter with a traditional news medium, New York Times, using unsupervised topic modeling, and finds interesting and useful findings for downstream IR or DM applications.
Empirical study of topic modeling in Twitter
1,138 Citations2010Liangjie Hong, Brian D. Davison
It is shown that by training a topic model on aggregated messages the authors can obtain a higher quality of learned model which results in significantly better performance in two real-world classification problems.
Topic modeling
1,057 Citations2006Hanna Wallach
A hierarchical generative probabilistic model that incorporates both n-gram statistics and latent topic variables by extending a unigram topic model to include properties of a hierarchical Dirichlet bigram language model is explored.
Neural Information Processing SystemsCorrelated Topic Models
929 Citations2005John Lafferty, David M. Blei
The correlated topic model (CTM) is developed, where the topic proportions exhibit correlation via the logistic normal distribution and a mean-field variational inference algorithm is derived for approximate posterior inference in this model, which is complicated by the fact that the Logistic normal is not conjugate to the multinomial.
Modeling online reviews with multi-grain topic models
792 Citations2008Ivan Titov, Ryan McDonald
This paper presents a novel framework for extracting ratable aspects of objects from online user reviews and argues that multi-grain models are more appropriate for this task since standard models tend to produce topics that correspond to global properties of objects rather than aspects of an object that tend to be rated by a user.
Management ScienceThe Structural Virality of Online Diffusion
649 Citations2015Sharad Goel, Ashton Anderson +2 more
This work proposes a formal measure of what it label “structural virality” that interpolates between two conceptual extremes: content that gains its popularity through a single, large broadcast and that which grows through multiple generations with any one individual directly responsible for only a fraction of the total adoption.
Journal of CommunicationThe Dynamics of Public Attention: Agenda-Setting Theory Meets Big Data
618 Citations2014W. Russell Neuman, Lauren Guggenheim +2 more
Improving LDA topic models for microblogs via tweet pooling and automatic labeling
472 Citations2013Rishabh Mehrotra, Scott Sanner +2 more
This paper empirically establishes that a novel method of tweet pooling by hashtags leads to a vast improvement in a variety of measures for topic coherence across three diverse Twitter datasets in comparison to an unmodified LDA baseline and a range of pooling schemes.
Journal of Broadcasting & Electronic MediaContent Analysis in an Era of Big Data: A Hybrid Approach to Computational and Manual Methods
399 Citations2013Seth C. Lewis, Rodrigo Zamith +1 more
It is argued that an approach blending computational and manual methods throughout the content analysis process may yield more fruitful results, and a case study of news sourcing on Twitter is drawn to illustrate this hybrid approach in action.
Sarcasm Detection on Twitter
364 Citations2015Ashwin Rajadesingan, Reza Zafarani +1 more
This paper employs theories from behavioral and psychological studies to construct a behavioral modeling framework tuned for detecting sarcasm on Twitter and identifies behavioral traits intrinsic to users expressing sarcasm using the user's past tweets.
Machine LearningInteractive topic modeling
342 Citations2013Yuening Hu, Jordan Boyd‐Graber +2 more
This paper presents a mechanism for giving users a voice by encoding users’ feedback to topic models as correlations between words into a topic model, and develops more efficient inference algorithms for tree-based topic models.
Journal of CommunicationExplicating Media Salience: A Factor Analysis of New York Times Issue Coverage During the 2000 U.S. Presidential Election
333 Citations2004Spiro Kiousis
Journal of CommunicationNetwork Issue Agendas on Twitter During the 2012 U.S. Presidential Election
237 Citations2014Chris J. Vargo, Лэй Гуо +2 more
Support for agenda melding is found and the Network Agenda Setting (NAS) model is validated through a series of computer science methods with large datasets on Twitter, which demonstrates that during the 2012 U.S. presidential election, distinctive audiences “melded” agendas of various media differently.
Journalism & Mass Communication QuarterlyA Content Analysis of Content Analyses: Twenty-Five Years of Journalism Quarterly
206 Citations1997Daniel Riffe, Alan R. Freitag
Journalism & Mass Communication QuarterlyThe Efficiency of Constructed Week Sampling for Content Analysis of Online News
196 Citations2007Joe Bob Hester, Elizabeth K. Dougall
Understanding the Limiting Factors of Topic Modeling via Posterior Contraction Analysis
184 Citations2014Jian Tang, Zhaoshi Meng +3 more
Greenwood Publishing Group Inc. eBooksTheory, Method, and Practice in Computer Content Analysis
124 Citations2001
A variety of methodological, theoretical, and practical issues are here addressed, presenting unique methods and perspectives for the consideration of computer content analysis.
Journalism & Mass Communication QuarterlyMass Communication Research Trends from 1980 to 1999
121 Citations2003Rasha Kamhawi, David Weaver
Lecture notes in computer scienceAnalyzing Entities and Topics in News Articles Using Statistical Topic Models
114 Citations2006David Newman, Chaitanya Chemudugunta +2 more
A novel combination of statistical topic models and named-entity recognizers are presented to jointly analyze entities mentioned and topics discussed in a collection of 330,000 New York Times news articles.
Communication Methods and MeasuresHow Much Is Enough? New Recommendations for Using Constructed Week Sampling in Newspaper Content Analysis of Health Stories
112 Citations2011Douglas A. Luke, Charlene Caburnay +1 more
This study uses Monte Carlo bootstrap sampling to determine the number of constructed weeks necessary to accurately estimate one- and five-year population values for different types of variables in a quantitative content analysis.
Quality & QuantityThematic content analysis using supervised machine learning: An empirical evaluation using German online news
107 Citations2011Michael Scharkow
Results indicate that supervised text classification is generally robust and reliable for some categories, but may even be useful when it fails, and investigates whether and how linguistic preprocessing can improve classification quality.
The Annals of the American Academy of Political and Social ScienceContent Analysis and the Algorithmic Coder
95 Citations2015Rodrigo Zamith, Seth C. Lewis
This article focuses on how the traditional (manual) approach to conducting a content analysis is being reconfigured, assesses what is gained and lost in turning to computational solutions, and builds on a “hybrid” approach to content analysis.
Journalism & Mass Communication QuarterlyThe Subjective Precision of Computers: A Methodological Comparison with Human Coding in Content Analysis
93 Citations2006Mike Conway
This methodological case study was designed to compare results of human versus computer-assisted coding using the same data set and found the two processes yielded significantly different results in a content analysis of newspaper coverage of a political campaign.
arXiv (Cornell University)Twitter Opinion Topic Model: Extracting Product Opinions from Tweets by Leveraging Hashtags and Sentiment Lexicon
66 Citations2016Kar Wai Lim, Wray Buntine
Self-disclosure topic model for classifying and analyzing Twitter conversations
58 Citations2014JinYeong Bak, Chin-Yew Lin +1 more
The developed self-disclosure topic model (SDTM) significantly outperforms several comparable methods on classifying the level of selfdisclosure, and the analysis of the longitudinal data using SDTM uncovers significant and positive correlation between self Disclosure and conversation frequency and length.
One theme in all views
54 Citations2013Jian Tang, Ming Zhang +1 more
A general solution that is able to exploit multiple types of contexts without arbitrary manipulation of the structure of classical topic models is proposed, and a co-regularization framework is proposed to let these views collaborate with each other, vote for the consensus topics, and distinguish them from view-specific topics.
TopicCheck: Interactive Alignment for Assessing Topic Model Stability
48 Citations2015Jason Chuang, Margaret E. Roberts +5 more
This work introduces TopicCheck, an interactive tool for assessing topic model stability, and devise an interactive alignment algorithm for matching latent topics from multiple models, and enable sensitivity evaluation across a large number of models.
Newspaper Research JournalCitizen Journalism Web Sites Complement Newspapers
47 Citations2010Stephen Lacy, Margaret Duffy +3 more
Journalism & Mass Communication QuarterlyOnline Information Sources of Political Blogs
44 Citations2009Mark Leccese
Twitter Opinion Topic Model
43 Citations2014Kar Wai Lim, Wray Buntine
It is shown that aspect-based opinion analysis on massive volume of tweets provides useful opinions on products, and a new formulation of incorporating sentiment prior information into a topic model, by utilizing an existing public sentiment lexicon is proposed.
Journal of International CommunicationChina's image on international English language social media
39 Citations2013Debao Xiang
Is the Internet a Positive Force in the Development of Civil Society, a Public Sphere, and Democratization in China?
30 Citations2010Stanley Rosen
Journalism & Mass Communication QuarterlyThe Effectiveness of Stratified Constructed Week Sampling for Content Analysis of Electronic News Source Archives: AP Newswire, Business Wire, and PR Newswire
28 Citations2009Colleen Connolly-Ahern, Lee Ahern +1 more
The results support the idea that as information passes through more media gatekeepers, who limit and standardize content, the sample sizes required for content analysis diminish.