Online abuse detection: the value of preprocessing and neural attention models

Dhruv Kumar, Robin Cohen, Lukasz Golab


Abstract
We propose an attention-based neural network approach to detect abusive speech in online social networks. Our approach enables more effective modeling of context and the semantic relationships between words. We also empirically evaluate the value of text pre-processing techniques in addressing the challenge of out-of-vocabulary words in toxic content. Finally, we conduct extensive experiments on the Wikipedia Talk page datasets, showing improved predictive power over the previous state-of-the-art.
Anthology ID:
W19-1303
Volume:
Proceedings of the Tenth Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Month:
June
Year:
2019
Address:
Minneapolis, USA
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16–24
Language:
URL:
https://aclanthology.org/W19-1303
DOI:
10.18653/v1/W19-1303
Bibkey:
Cite (ACL):
Dhruv Kumar, Robin Cohen, and Lukasz Golab. 2019. Online abuse detection: the value of preprocessing and neural attention models. In Proceedings of the Tenth Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 16–24, Minneapolis, USA. Association for Computational Linguistics.
Cite (Informal):
Online abuse detection: the value of preprocessing and neural attention models (Kumar et al., WASSA 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-1303.pdf
Code
 ddhruvkr/Online_Abuse_Detection