A Study on Opinion Mining of Newspaper Texts based on Topic Modeling

Abstract

This study performs opinion mining of newspaper articles, based on topics extracted by topic modeling. We analyze the attitudes of the news media towards a major issue of 'presidential election', assuming that newspaper partisanship is a kind of opinion. We first extract topics from a large collection of newspaper texts, and examine how the topics are distributed over the entire dataset. The structure and content of each topic are then investigated by means of network analysis. Finally we track down the chronological distribution of the topics in each of the newspapers through time serial analysis. The result reveals that both the liberal newspapers and the conservative newspapers exhibit their own tendency to report in line with their adopted ideology. This confirms that we can count on opinion mining technique based on topics in order to analyze opinion in a reliable fashion.

Gatekeeping Fake News Discourses on Mainstream Media Versus Social Media

“…In the study that employs factor analysis (FA), the latent semantic concepts are identified in the examined data. Many research studies employed topic modeling using different procedures and types of software such as the study of large data sets on Twitter (Conover, Ferrara, Menczer, & Flammini, 2013;Ghosh & Guha, 2013), especially that this online platform has become an important venue for news and political opinions (Dyagilev & Yom-Tov, 2014;Vergeer, 2015), while other studies use and/or reference topic modeling in public comments, forums, and journalism-related issues (Berendt, 2011;Boumans & Trilling, 2016;Jacobi, van Atteveldt, & Welbers, 2016;Kigerl, 2017), especially in examining some case studies in media coverage (DiMaggio, Nag, & Blei, 2013;Kang, Song & Jho, 2013;Levy & Franklin, 2014).…”

News Values on Instagram: A Comparative Study of International News

“…Due to the large dataset, we employed topic modeling, which normally "generate[s] words based on latent topic variables inferred from word correlations independent of the order in which the words appear" (Wallach 2006). Many studies have used topic modeling to study news coverage of certain topics, including big data on Twitter, online comments, and various issues in journalism (Berendt 2011;Boumans and Trilling 2016;Conover et al 2013;DiMaggio et al 2013;Ghosh and Guha 2013;Jacobi et al 2016;Kang et al 2013;Kigerl 2017;Levy and Franklin 2014). For this study, we employed Factor Analysis (FA) in our topic modeling approach in order to identify the latent semantic concepts.…”

Intersecting violence: Representations of Somali youth in the Canadian press

“…Topic modeling technique identifies the most recurrent topics found in an unstructured corpus with the use of a statistical model and algorithm; it is part of machine learning that calculates the most frequent words and phrases used and their associations with other terms. Topic modeling has been used in journalism-related studies (Al-Rawi, 2018b; Berendt, 2011; Boumans and Trilling, 2016; Jacobi et al, 2016) such as examining a number of case studies in media coverage (Kang et al, 2013; DiMaggio et al, 2013).…”