Gao, Wang and Fang, Yuan and Li, Lin and Tao, Xiaohui 
ORCID: https://orcid.org/0000-0002-0020-077X
(2021)
Event Detection in Social Media via Graph Neural Network.
In: 22nd International Conference on Web Information Systems Engineering, Part I (WISE 2021), 26 Oct - 29 Oct 2021, Melbourne, Australia.
Abstract
Recently, Graph Neural Networks (GNN) have been applied to many natural language processing tasks. However, few studies exploit GNN for event detection, especially event detection in social media. In this paper, we proposed a new Event Detection model based on GNN (EDGNN). EDGNN first utilizes a topic model to capture the topical information of the corpus, which is used to help the graph enrich the semantics of short texts. Then, a text-level graph with fewer edges and memory consumption is constructed for each input short text. Furthermore, we incorporate word embeddings trained by Bidirectional Encoder Representations from Transformers (BERT) into EDGNN, which greatly improves the performance of the proposed method. Experimental results on a real-world foodborne disease event dataset demonstrate our model outperforms state-of-the-art baselines.
|
Statistics for this ePrint Item |
Actions (login required)
 |
Archive Repository Staff Only |