“A Little Birdie Told Me ... ” - Inductive Biases for Rumour Stance Detection on Social Media

Karthik Radhakrishnan, Tushar Kanakagiri, Sharanya Chakravarthy, Vidhisha Balachandran


Abstract
The rise in the usage of social media has placed it in a central position for news dissemination and consumption. This greatly increases the potential for proliferation of rumours and misinformation. In an effort to mitigate the spread of rumours, we tackle the related task of identifying the stance (Support, Deny, Query, Comment) of a social media post. Unlike previous works, we impose inductive biases that capture platform specific user behavior. These biases, coupled with social media fine-tuning of BERT allow for better language understanding, thus yielding an F1 score of 58.7 on the SemEval 2019 task on rumour stance detection.
Anthology ID:
2020.wnut-1.31
Volume:
Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
244–248
Language:
URL:
https://aclanthology.org/2020.wnut-1.31
DOI:
10.18653/v1/2020.wnut-1.31
Bibkey:
Cite (ACL):
Karthik Radhakrishnan, Tushar Kanakagiri, Sharanya Chakravarthy, and Vidhisha Balachandran. 2020. “A Little Birdie Told Me ... ” - Inductive Biases for Rumour Stance Detection on Social Media. In Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020), pages 244–248, Online. Association for Computational Linguistics.
Cite (Informal):
“A Little Birdie Told Me … ” - Inductive Biases for Rumour Stance Detection on Social Media (Radhakrishnan et al., WNUT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.wnut-1.31.pdf
Optional supplementary material:
 2020.wnut-1.31.OptionalSupplementaryMaterial.pdf