Towards offensive language detection and reduction in four Software Engineering communities

TL;DR

This paper investigates offensive language in four major Software Engineering communities, proposing a deep learning-based detection approach and a Conflict Reduction System to minimize offensive comments and improve community engagement.

Contribution

It introduces a novel deep learning method for detecting offensive language in SE communities and presents a Conflict Reduction System to suggest modifications for reducing offence.

Findings

Offensive language prevalence ranges from 0.07% to 0.43% across communities.

The detection approach shows promising accuracy in classifying offensive comments.

The CRS can significantly reduce manual moderation efforts.

Abstract

Software Engineering (SE) communities such as Stack Overflow have become unwelcoming, particularly through members' use of offensive language. Research has shown that offensive language drives users away from active engagement within these platforms. This work aims to explore this issue more broadly by investigating the nature of offensive language in comments posted by users in four prominent SE platforms - GitHub, Gitter, Slack and Stack Overflow (SO). It proposes an approach to detect and classify offensive language in SE communities by adopting natural language processing and deep learning techniques. Further, a Conflict Reduction System (CRS), which identifies offence and then suggests what changes could be made to minimize offence has been proposed. Beyond showing the prevalence of offensive language in over 1 million comments from four different communities which ranges from 0.07% to 0.43%, our results show promise in successful detection and classification of such language. The CRS system has the potential to drastically reduce manual moderation efforts to detect and reduce offence in SE communities.