Logo image
Empirical Analysis of Multi-Task Learning for Reducing Identity Bias in Toxic Comment Detection
Journal article   Open access

Empirical Analysis of Multi-Task Learning for Reducing Identity Bias in Toxic Comment Detection

Ameya Vaidya, Feng Mai and Yue Ning
Proceedings of the International AAAI Conference on Web and Social Media, Vol.14, pp.683-693
05/26/2020
DOI: 10.1609/icwsm.v14i1.7334
url
https://doi.org/10.1609/icwsm.v14i1.7334View
Published (Version of record) Open Access

Abstract

With the recent rise of toxicity in online conversations on social media platforms, using modern machine learning algorithms for toxic comment detection has become a central focus of many online applications. Researchers and companies have developed a variety of models to identify toxicity in online conversations, reviews, or comments with mixed successes. However, many existing approaches have learned to incorrectly associate non-toxic comments that have certain trigger-words (e.g. gay, lesbian, black, muslim) as a potential source of toxicity. In this paper, we evaluate several state-of-the-art models with the specific focus of reducing model bias towards these commonly-attacked identity groups. We propose a multi-task learning model with an attention layer that jointly learns to predict the toxicity of a comment as well as the identities present in the comments in order to reduce this bias. We then compare our model to an array of shallow and deep-learning models using metrics designed especially to test for unintended model bias within these identity groups.

Details

Metrics

12 Record Views
Logo image