Net-TF-SW: Event Popularity Quantification with Network Structure

Hiroshi Nagaya; Teruaki Hayashi; Yukio Ohsawa; Fujio Toriumi; Hiroyuki A Torii; Kazuko Uno

doi:10.1016/j.procs.2020.09.194

Net-TF-SW: Event Popularity Quantification with Network Structure

Procedia Comput Sci. 2020:176:1693-1702. doi: 10.1016/j.procs.2020.09.194. Epub 2020 Oct 2.

Authors

Hiroshi Nagaya¹, Teruaki Hayashi¹, Yukio Ohsawa¹, Fujio Toriumi¹, Hiroyuki A Torii², Kazuko Uno³

Affiliations

¹ School of Engineering, The University of Tokyo, 7-3-1 Hongo Bunkyo-ku, Tokyo, 113-8656, Japan.
² School of Science, The University of Tokyo, 7-3-1 Hongo Bunkyo-ku, Tokyo, 113-0033, Japan.
³ Louis Pasteur Center for Medical Research, 103-5, Tanaka Monzen-cho, Sakyo-ku, Kyoto City, Kyoto, 606-8225, Japan.

Abstract

Event popularity quantification is essential in the determination of current trends in events on social media and the internet. Particularly, it is important during a crisis to ensure appropriate information transmission and prevention of false-rumor diffusion. Here, we propose Net-TF-SW - a noise-robust and explainable topic popularity analysis method. This method is applied to tweets related to COVID-19 and the Fukushima Daiichi Nuclear Disaster, which are two significant crises that have caused significant anxiety and confusion among Japanese citizens. The proposed method is compared to existing methods, and it is verified to be more robust with respect to noise.

Keywords: COVID-19; Data Mining; Event Popularity; Fukushima Daiichi Nuclear Disaster; Social Media.