Social event detection with reinforced deep heterogeneous graph attention network

Social Event Detection has become increasingly important as a way of letting the public know about significant global events in a clear and timely fashion. However, current methods are still unsatisfactory for detecting events due to the complexity of reality social networks. Specifically, there exist overlinks for partial nodes (i.e., messages), and conversely, some nodes lack sufficient neighborhood information. In addition, the time interval between different messages in social networks should also be fully considered by existing shallow GNN models. What is needed is an approach that can improve the embedding ability of GNN models by extracting and aggregating more se-mantic and structural information from the same graph for more representative and robust message embeddings, rather than constructing a richer message graph by adding additional attributed data. To this end, we design an innovative Reinforced Deep Heterogeneous Graph Attention Network (Re-DHAN) method for offline and incremental social event detection tasks. The framework initially leverages multi-agent reinforcement learning to select the most meaningful neighbors from various meta-path graphs to avoid redundant links. Then, our approach adds temporal convolutional attention across the semantics and timestamps for all nodes, ensuring a comprehensive capture of both semantic and time elements within social networks. Finally, to ensure that the embeddings produced by DHAN are both robust to too few neighbors and highly representative, we constructed a new Dual Graph Contrastive Learning model, called DGCL, to simulate the missing structural information. DGCL includes a triplet loss function and an unsupervised GraphCL model with multi-scaled subgraph augmentation. A series of experiments in offline and incremental social event detection demonstrates Re-DHAN as superior to the current state-of-the-art baselines. Furthermore, the results show that our ReDHAN has powerful and robust abilities to capture, extract, and aggregate the semantic and structural information within graphs.