It’s about Time: Rethinking Evaluation on Rumor Detection Benchmarks using Chronological Splits

Yida Mu, Kalina Bontcheva, Nikolaos Aletras


Abstract
New events emerge over time influencing the topics of rumors in social media. Current rumor detection benchmarks use random splits as training, development and test sets which typically results in topical overlaps. Consequently, models trained on random splits may not perform well on rumor classification on previously unseen topics due to the temporal concept drift. In this paper, we provide a re-evaluation of classification models on four popular rumor detection benchmarks considering chronological instead of random splits. Our experimental results show that the use of random splits can significantly overestimate predictive performance across all datasets and models. Therefore, we suggest that rumor detection models should always be evaluated using chronological splits for minimizing topical overlaps.
Anthology ID:
2023.findings-eacl.55
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
736–743
Language:
URL:
https://aclanthology.org/2023.findings-eacl.55
DOI:
10.18653/v1/2023.findings-eacl.55
Bibkey:
Cite (ACL):
Yida Mu, Kalina Bontcheva, and Nikolaos Aletras. 2023. It’s about Time: Rethinking Evaluation on Rumor Detection Benchmarks using Chronological Splits. In Findings of the Association for Computational Linguistics: EACL 2023, pages 736–743, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
It’s about Time: Rethinking Evaluation on Rumor Detection Benchmarks using Chronological Splits (Mu et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-eacl.55.pdf
Video:
 https://aclanthology.org/2023.findings-eacl.55.mp4