Claim-Centric and Sentiment Guided Graph Attention Network for Rumour Detection

Sajad Ramezani, Mauzama Firdaus, Lili Mou

Abstract
Automatic rumour detection has gained attention due to the influence of social media on individuals and its pervasiveness. In this work, we construct a representation that takes into account the claim in the source tweet, considering both the propagation graph and the accompanying text alongside tweet sentiment. This is achieved through the implementation of a hierarchical attention mechanism, which not only captures the embedding of documents from individual word vectors but also combines these document representations as nodes within the propagation graph. Furthermore, to address potential overfitting concerns, we employ generative models to augment the existing datasets. This involves rephrasing the claims initially made in the source tweet, thereby creating a more diverse and robust dataset. In addition, we augment the dataset with sentiment labels to improve the performance of the rumour detection task. This holistic and refined approach yields a significant enhancement in the performance of our model across three distinct datasets designed for rumour detection. Quantitative and qualitative analysis proves the effectiveness of our methodology, surpassing the achievements of prior methodologies.
Anthology ID:
2024.lrec-main.287
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
3235–3241
Language:
URL:
https://aclanthology.org/2024.lrec-main.287
DOI:
Bibkey:
Cite (ACL):
Sajad Ramezani, Mauzama Firdaus, and Lili Mou. 2024. Claim-Centric and Sentiment Guided Graph Attention Network for Rumour Detection. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3235–3241, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Claim-Centric and Sentiment Guided Graph Attention Network for Rumour Detection (Ramezani et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2024.lrec-main.287.pdf
PDF Search