Mining Media Topics Perceived as Social Problems by Online Audiences: Use of a Data Mining Approach in Sociology

Abstract

Media audiences that represent a significant part of a county’s public may hold opinions on media-generated definitions of social problems different from those of media professionals. The proliferation of user-generated content makes such opinions available, but simultaneously demands new automatic methods of analysis that media scholars still have to master. In this paper, we show how topics regarded as problematic by media consumers may be revealed and analyzed by social scientists with a combination of data mining methods. Our dataset consists of 33,877 news items and 258,121 comments from a sample of regional newspapers. With a number of new, but simple indices we find that issue salience in media texts and its popularity with audience diverge. We conclude that our approach can help communication scholars effectively detect both popular and negatively perceived topics as good proxies of social problems.

Keywords: social problem, online media, topic modeling, sentiment analysis, Russia

JEL Classification: Z