XFake: Explainable Fake News Detector with Visualizations Conference Paper uri icon

abstract

  • 2019 IW3C2 (International World Wide Web Conference Committee), published under Creative Commons CC-BY 4.0 License. In this demo paper, we present the XFake system, an explainable fake news detector that assists end-users to identify news credibility. To effectively detect and interpret the fakeness of news items, we jointly consider both attributes (e.g., speaker) and statements. Specifically, MIMIC, ATTN and PERT frameworks are designed, where MIMIC is built for attribute analysis, ATTN is for statement semantic analysis and PERT is for statement linguistic analysis. Beyond the explanations extracted from the designed frameworks, relevant supporting examples as well as visualization are further provided to facilitate the interpretation. Our implemented system is demonstrated on a real-world dataset crawled from PolitiFact1, where thousands of verified political news have been collected.

name of conference

  • The World Wide Web Conference

published proceedings

  • WEB CONFERENCE 2019: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2019)

altmetric score

  • 7.1

author list (cited authors)

  • Yang, F., Pentyala, S. K., Mohseni, S., Du, M., Yuan, H., Linder, R., ... Hu, X. B.

citation count

  • 32

complete list of authors

  • Yang, Fan||Pentyala, Shiva K||Mohseni, Sina||Du, Mengnan||Yuan, Hao||Linder, Rhema||Ragan, Eric D||Ji, Shuiwang||Hu, Xia Ben

publication date

  • January 2019