JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM ›› 2020, Vol. 22 ›› Issue (1): 1-6.doi: 10.19722/j.cnki.1008-7729.2019.0369

    Next Articles

Content Detection Based on Knowledge Relation: Cases of Health Rumors


  1. School of Digital Media and Design Arts, Beijing University of Posts
    and Telecommunications, Beijing 100876, China
  • Received:2019-11-08 Online:2020-02-28

Abstract: Ubiquitous informatization in the society enables the Internet to be the most efficient access for acquiring knowledge However, with the decrease of barriers for releasing and distributing information, frequent occurrence of rumors has become a social problem Moreover, health topics are closely related to individuals lives, so they are the worst-hit area of rumors Based on content analysis of rumors in WeChat and Toutiaocom, the research question of how to detect rumors through the characteristics of knowledge relation is proposed In order to explore and present the knowledge relation, a social networking analysis tool was adopted to visualize the cluster of high frequency words of weight-loss rumors that were refined from the rumor base at Bytedance With the analysis through visualization, it is found that the co-occurrence relation is better than the similarity relation at discovering common phrases and popular topics of knowledge-based rumors Lastly, in a normative perspective, a mechanism for detecting newborn rumors is constructed, which should integrate technologies of knowledge graph and labeling

Key words: content detection, knowledge relation, cooccurrence relation

CLC Number: