RumorLens: Interactive Analysis and Validation of Suspected Rumors on Social Media

• DOI: 10.1145/3491101.3519712
• Publication Date: 2022-04-29T16:49:48Z
• Authors: Ran Wang; Kehan Du; Qianhe Chen; Yifei Zhao; Mojie Tang; Hongxi Tao; Shipan Wang; Yiyao Li; Yong Wang
• Keywords: Rumor; Glyph (data visualization)

With the development of social media, various rumors can be easily spread on Internet and such have serious negative effects society. Thus, it has become a critical task for media platforms to deal with suspected rumors. However, due lack effective tools, is often difficult platform administrators analyze validate from large volume information efficiently. We worked closely four months summarize their requirements identifying analyzing rumors, further proposed an interactive visual analytics system, RumorLens, help them rumor efficiently gain in-depth understanding patterns spreading. RumorLens integrates natural language processing (NLP) other data techniques visualization facilitate analysis validation propose well-coordinated visualizations provide users three levels details rumors: overview displays both spatial distribution temporal evolution rumors; projection view leverages metaphor-based glyph represent each enable quick overall characteristics similarity other; propagation visualizes dynamic spreading novel circular design, facilitates in compact manner. By using real-world dataset collected Sina Weibo, one case study domain expert conducted evaluate RumorLens. The results demonstrated usefulness effectiveness our approach.