Preemptive Toxic Language Detection in Wikipedia Comments Using Thread-Level Context

Mladen Karan, Jan Šnajder


Abstract
We address the task of automatically detecting toxic content in user generated texts. We fo cus on exploring the potential for preemptive moderation, i.e., predicting whether a particular conversation thread will, in the future, incite a toxic comment. Moreover, we perform preliminary investigation of whether a model that jointly considers all comments in a conversation thread outperforms a model that considers only individual comments. Using an existing dataset of conversations among Wikipedia contributors as a starting point, we compile a new large-scale dataset for this task consisting of labeled comments and comments from their conversation threads.
Anthology ID:
W19-3514
Volume:
Proceedings of the Third Workshop on Abusive Language Online
Month:
August
Year:
2019
Address:
Florence, Italy
Venue:
ALW
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
129–134
Language:
URL:
https://aclanthology.org/W19-3514
DOI:
10.18653/v1/W19-3514
Bibkey:
Cite (ACL):
Mladen Karan and Jan Šnajder. 2019. Preemptive Toxic Language Detection in Wikipedia Comments Using Thread-Level Context. In Proceedings of the Third Workshop on Abusive Language Online, pages 129–134, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Preemptive Toxic Language Detection in Wikipedia Comments Using Thread-Level Context (Karan & Šnajder, ALW 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-3514.pdf