Detecting Community Sensitive Norm Violations in Online Conversations

Chan Young Park, Julia Mendelsohn, Karthik Radhakrishnan, Kinjal Jain, Tushar Kanakagiri, David Jurgens, Yulia Tsvetkov


Abstract
Online platforms and communities establish their own norms that govern what behavior is acceptable within the community. Substantial effort in NLP has focused on identifying unacceptable behaviors and, recently, on forecasting them before they occur. However, these efforts have largely focused on toxicity as the sole form of community norm violation. Such focus has overlooked the much larger set of rules that moderators enforce. Here, we introduce a new dataset focusing on a more complete spectrum of community norms and their violations in the local conversational and global community contexts. We introduce a series of models that use this data to develop context- and community-sensitive norm violation detection, showing that these changes give high performance.
Anthology ID:
2021.findings-emnlp.288
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venues:
EMNLP | Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3386–3397
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.288
DOI:
10.18653/v1/2021.findings-emnlp.288
Bibkey:
Cite (ACL):
Chan Young Park, Julia Mendelsohn, Karthik Radhakrishnan, Kinjal Jain, Tushar Kanakagiri, David Jurgens, and Yulia Tsvetkov. 2021. Detecting Community Sensitive Norm Violations in Online Conversations. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3386–3397, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Detecting Community Sensitive Norm Violations in Online Conversations (Park et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.288.pdf
Code
 chan0park/normvio