The authors introduce AMG, an attribution-labeled multimodal fake news benchmark with five fake patterns, plus MGCA, a clue-alignment model that outperforms baselines on it.
Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News Detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Fake news detection has been a critical task for maintaining the health of the online news ecosystem. However, very few existing works consider the temporal shift issue caused by the rapidly-evolving nature of news data in practice, resulting in significant performance degradation when training on past data and testing on future data. In this paper, we observe that the appearances of news events on the same topic may display discernible patterns over time, and posit that such patterns can assist in selecting training instances that could make the model adapt better to future data. Specifically, we design an effective framework FTT (Forecasting Temporal Trends), which could forecast the temporal distribution patterns of news data and then guide the detector to fast adapt to future distribution. Experiments on the real-world temporally split dataset demonstrate the superiority of our proposed framework. The code is available at https://github.com/ICTMCG/FTT-ACL23.
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Each Fake News is Fake in its Own Way: An Attribution Multi-Granularity Benchmark for Multimodal Fake News Detection
The authors introduce AMG, an attribution-labeled multimodal fake news benchmark with five fake patterns, plus MGCA, a clue-alignment model that outperforms baselines on it.