Rumor Detection on Social Media via Fused Semantic Information and a Propagation Heterogeneous Graph

Abstract

Social media had a revolutionary impact because it provides an ideal platform for share information; however, it also leads to the publication and spreading of rumors. Existing rumor detection methods have relied on finding cues from only user-generated content, user profiles, or the structures of wide propagation. However, the previous works have ignored the organic combination of wide dispersion structures in rumor detection and text semantics. To this end, we propose KZWANG, a framework for rumor detection that provides sufficient domain knowledge to classify rumors accurately, and semantic information and a propagation heterogeneous graph are symmetry fused together. We utilize an attention mechanism to learn a semantic representation of text and introduce a GCN to capture the global and local relationships among all the source microblogs, reposts, and users. An organic combination of text semantics and propagating heterogeneous graphs is then used to train a rumor detection classifier. Experiments on Sina Weibo, Twitter15, and Twitter16 rumor detection datasets demonstrate the proposed model’s superiority over baseline methods. We also conduct an ablation study to understand the relative contributions of the various aspects of the method we proposed.

Rumor Detection with Bidirectional Graph Attention Networks

“…On the basis of constructing an undirected tree, GCN is used to perform top-down and bottom-up convolution of the tree structure to express the propagation and diffusion of rumors. KZWANG [20]: a rumor detection method based on graph neural network and attention mechanism. DTC [1]: a rumor detection method that manually extracts multiple global features and uses decision trees for classification.…”

“…Bian et al [19] obtained the propagation and diffusion features of rumors through top-down and bottom-up node updates and proposed a rumor detection model with bidirectional graph convolutional network. Ke et al [20] proposed constructing the global relationship between all source tweets, response tweets, and users as a heterogeneous graph to obtain interactive feature information. Dou et al [21] proposed a rumor detection method based on a multirelational propagation tree, which comprehensively considers the interlayer dependencies and intralayer dependencies of nodes.…”

Location and Language Independent Fake Rumor Detection Through Epidemiological and Structural Graph Analysis of Social Connections

“…The experimental results of the baseline models that appear in Table 8 are drawn from the literature (Yuan, 2019 ; Ke et al, 2020 ). As Table 8 shows, our approach achieves results that rank it in the top 7 approaches for Twitter15 and the top 5 for Twitter16, in regard to accuracy, relatively to the 10 alternatives included in Table 8 .…”

Analyzing Sentiments and Diffusion Characteristics of COVID-19 Vaccine Misinformation Topics in Social Media

“…In contrast, non-misinformation refers to information that is judged to be correct by relevant experts at a given point in time based on the best available evidence (Loomba et al, 2021). In a study on rumor detection in social media, Ke et al (2020) showed that user credibility and microblog trustworthiness can be best characterized by including three types of attributes in the classification model: microblog attributes (including the number of retweets, likes, and replies), user attributes (including the number of followers, fans, and whether they are authenticated), and text-topic distribution. Accordingly, we classified tweets as misinformation or non-misinformation based on subsequent consideration of tweets and user attributes describing user trustworthiness and reliability.…”