1 April 2016 in Journalism & Mass Communication Quarterly
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.
4 June 2018 in Communication Research
This study examined how fake news, misinformation, and satire, affected the emerging media ecosystem during the 2016 U.S. presidential election through an integrated intermedia agenda-setting analysis, which studies broad attributes and myopic stories and events. A computer-assisted content analysis of millions of news articles was conducted alongside a qualitative analysis of popular news headlines and articles. The results showed that websites that spread misinformation had a fairly close intermedia agenda-setting relationship with fact-based media in covering Trump, but not for the news about Clinton. Satire websites barely interacted with the agenda of other media outlets. Overall, it seemed that rather than playing a unique agenda-setting role in this emerging media landscape, fake news websites added some noise to an already sensationalized news environment.
5 July 2017 in Journal of Communication
20 July 2018 in Information, Communication & Society
This study examined the echo chamber phenomenon and opinion leadership on Twitter based on the 2016 U.S. presidential election. Network analysis and ‘big data’ analytics were employed to analyze more than 50 million tweets about the two presidential candidates, Donald Trump and Hillary Clinton, during the election cycle. Overall, the results suggested that Twitter communities discussing Trump and Clinton differed significantly in the level of political homogeneity and opinion leadership, and that certain opinion leaders were responsible of creating homogeneous communities on Twitter. This study made a theoretical contribution to the literature by linking opinion leadership and Twitter’s network structure and shedding light on what may have caused the echo chamber problem to happen in an emerging media landscape.
2 June 2020 in Digital Journalism
This study examines the “fake news” problem in China where the media environment is tightly controlled. Focusing on online rumors that are not politically sensitive, this article seeks to shed light on a commercialized dimension of China’s online media landscape in addition to a highly politicalized one that previous research has emphasized. Based on an intermedia agenda-setting analysis of the top ten rumors circulated on China’s Internet in 2016, this study demonstrates that although the government-controlled news websites challenged the rumors to a great extent, they also contributed to the perpetration of misinformation. Even the national official media advanced some rumors themselves and induced other media outlets to do so.