본문 바로가기
  • Home

Text Mining Driven Content Analysis of Ebola on News Media and Scientific Publications

An Juyoung 1 kyubin, Ahn 2 Min Song 2

1연세대학교 문헌정보학과
2연세대학교

Accredited

ABSTRACT

Infectious diseases such as Ebola virus disease become a social issue and draw public attention to be a major topic on news or research. As a result, there have been a lot of studies on infectious diseases using text-mining techniques. However, there is no research on content analysis of two media channels that have distinct characteristics. Accordingly, in this study, we conduct topic analysis between news (representing a social perspective) and academic research paper (representing perspectives of bio-professionals). As text-mining techniques, topic modeling is applied to extract various topics according to the materials, and the word co-occurrence map based on selected bio entities is used to compare the perspectives of the materials specifically. For network analysis, topic map is built by using Gephi. Aforementioned approaches uncovered the difference of topics between two materials and the characteristics of the two materials. In terms of the word co-occurrence map, however, most of entities are shared in both materials. These results indicate that there are differences and commonalties between social and academic materials.

Citation status

* References for papers published after 2022 are currently being built.