Multi-Semantics Learning for Social Event Detection via Heterogeneous GNNs

Abstract

Events spreading on social media platforms reflect current public concerns and emotions among public opinions. Heterogeneous elements of social networks and the sparse context of social messages bring significant challenges to the fine-grained social event detection task. Few existing methods can learn the inherent structure and rich semantics among social messages, nor can they effectively update the detection model in a dynamic scenario for continuously coming messages. In this paper, we design a novel Multi-Semantics Heterogeneous Graph Neural Network (MSGNN) to learn social events in a continuous detection framework. We apply the heterogeneous information network (HIN) to modeling social events, considering the heterogeneous elements and meta-paths in the social event data stream. We propose a dual-level messages aggregation mechanism to aggregate semantics between heterogeneous elements, which aggregates the local features of adjacent neighboring messages from the node level and the global semantics from the meta-path level to the current message. A semantic weight is designed for messages to filter out noise under social message streams. We conduct extensive experiments on two real-world social event datasets, and the experimental results demonstrate that our proposed model outperforms state-of-the-art models.