Event Detection in Social Media via Graph Neural Network
Paper
Paper/Presentation Title | Event Detection in Social Media via Graph Neural Network |
---|---|
Presentation Type | Paper |
Authors | Gao, Wang (Author), Fang, Yuan (Author), Li, Lin (Author) and Tao, Xiaohui (Author) |
Editors | Zhang, Wenjie, Zou, Lei, Maamar, Zakaria and Chen, Lu |
Journal or Proceedings Title | Lecture Notes in Computer Science (Book series) |
ERA Conference ID | 43582 |
Journal Citation | 13080, pp. 370-384 |
Number of Pages | 15 |
Year | 2021 |
Publisher | Springer |
Place of Publication | Switzerland |
ISSN | 1611-3349 |
0302-9743 | |
ISBN | 9783030908874 |
9783030908881 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-030-90888-1_28 |
Web Address (URL) of Paper | https://link.springer.com/chapter/10.1007/978-3-030-90888-1_28 |
Conference/Event | 22nd International Conference on Web Information Systems Engineering, Part I (WISE 2021) |
International Conference on Web Information Systems Engineering | |
Event Details | International Conference on Web Information Systems Engineering WISE Rank A A A A A A A A A A A A A A A A A A A |
Event Details | 22nd International Conference on Web Information Systems Engineering, Part I (WISE 2021) Event Date 26 to end of 29 Oct 2021 Event Location 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. |
Keywords | Event detection; Graph neural network; Topic model; BERT |
ANZSRC Field of Research 2020 | 460208. Natural language processing |
460502. Data mining and knowledge discovery | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Jianghan University, China |
Wuhan University of Technology, China | |
School of Sciences | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q6z54/event-detection-in-social-media-via-graph-neural-network
156
total views7
total downloads2
views this month0
downloads this month