Sentiment Analysis of Polarizing Topics in Social Media: News Site Readers’ Comments on the Trayvon Martin Controversy
Communication and Information Technologies Annual
ISBN: 978-1-78560-785-1, eISBN: 978-1-78560-784-4
Publication date: 23 February 2016
Abstract
Purpose
The authors apply topic sentiment analysis (several relatively new text analysis methods) to the study of public opinion as expressed in social media by comparing reactions to the Trayvon Martin controversy in spring 2012 by commenters on the partisan news websites the Huffington Post and Daily Caller.
Methodology/approach
Topic sentiment analysis is a text analysis method that estimates the polarity of sentiments across units of text within large text corpora (Lin & He, 2009; Mei, Ling, Wondra, Su, & Zhai, 2007).
Findings
We apply topic sentiment analysis to public opinion as expressed in social media by comparing reactions to the Trayvon Martin controversy in spring 2012 by commenters on the partisan news websites the Huffington Post and Daily Caller. Based on studies that depict contemporary news media as an “outrage industry” that incentivizes media personalities to be controversial and polarizing (Berry & Sobieraj, 2014), we predict that high-profile commentators will be more polarizing than other news personalities and topics.
Originality/value
Results of the topic sentiment analysis support this prediction and in so doing provide partial validation of the application of topic sentiment analysis to online opinion.
Keywords
Acknowledgements
Acknowledgment
This is a revision of a paper presented at the 2014 American Sociological Association Annual Meeting in San Francisco at the section on social psychology paper session, Computational Social Science and Studying Social Behavior.
Citation
Ignatow, G., Evangelopoulos, N. and Zougris, K. (2016), "Sentiment Analysis of Polarizing Topics in Social Media: News Site Readers’ Comments on the Trayvon Martin Controversy", Communication and Information Technologies Annual (Studies in Media and Communications, Vol. 11), Emerald Group Publishing Limited, Leeds, pp. 259-284. https://doi.org/10.1108/S2050-206020160000011021
Publisher
:Emerald Group Publishing Limited
Copyright © 2016 Emerald Group Publishing Limited