Abstract
Proactively identifying misinformation spreaders is an important step towards mitigating the impact of fake news on our society. Although the news domain is subject to rapid changes over time, the temporal dynamics of the spreaders’ language and network have not been explored yet. In this paper, we analyze the users’ time-evolving semantic similarities and social interactions and show that such patterns can, on their own, indicate misinformation spreading. Building on these observations, we propose a dynamic graph-based framework that leverages the dynamic nature of the users’ network for detecting fake news spreaders. We validate our design choice through qualitative analysis and demonstrate the contributions of our model’s components through a series of exploratory and ablative experiments on two datasets.- Anthology ID:
- 2022.textgraphs-1.10
- Volume:
- Proceedings of TextGraphs-16: Graph-based Methods for Natural Language Processing
- Month:
- October
- Year:
- 2022
- Address:
- Gyeongju, Republic of Korea
- Editors:
- Dmitry Ustalov, Yanjun Gao, Alexander Panchenko, Marco Valentino, Mokanarangan Thayaparan, Thien Huu Nguyen, Gerald Penn, Arti Ramesh, Abhik Jana
- Venue:
- TextGraphs
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 89–104
- Language:
- URL:
- https://aclanthology.org/2022.textgraphs-1.10
- DOI:
- Cite (ACL):
- Joan Plepi, Flora Sakketou, Henri-Jacques Geiss, and Lucie Flek. 2022. Temporal Graph Analysis of Misinformation Spreaders in Social Media. In Proceedings of TextGraphs-16: Graph-based Methods for Natural Language Processing, pages 89–104, Gyeongju, Republic of Korea. Association for Computational Linguistics.
- Cite (Informal):
- Temporal Graph Analysis of Misinformation Spreaders in Social Media (Plepi et al., TextGraphs 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2022.textgraphs-1.10.pdf