A Novel Rumor Detection Method Based on Non-Consecutive Semantic Features and Comment Stance

Abstract

Detecting rumors on social media has become increasingly necessary due to their rapid spread and adverse impact on society. Currently, most rumor detection methods fail to consider the non-consecutive semantic features of the post’s text or the authority of commenting users. Therefore, we propose a novel rumor detection method that integrates non-consecutive semantic features and stances considering user weights. Firstly, we employ a pre-trained stance detection model to extract stance information for each comment for the post and then determine the weight of the stance information based on commenting user characteristics. Secondly, we input the time-series data of stance information and the corresponding comment user sequence data into the Cross-modal Transformer to learn the temporal features of comment stances. We then use pointwise mutual information to transform the discretized and fragmented post’s text into a weighted graph and utilize a graph attention network that considers edge weights to process the graph and learn the non-consecutive semantic features of the text. Finally, we concatenate the temporal features of comment stances with the non-consecutive semantic features of the post’s text and input them into a multi-layer perceptron for rumor classification. Experimental results on two public social media rumor datasets, Weibo and PHEME, demonstrate that our method outperforms the baselines. Our method is at least 12 hours ahead of the baseline methods for early rumor detection.

Keywords

• Rumor detection
• non-consecutive semantic features
• weighted graph attention network
• cross-modal transformer
• attention mechanism
• deep learning