HateClassify: A Service Framework for Hate Speech Identication on Social Media

Khan, Muhammad Usman Shahid, Abbas, Assad, Rehman, Attiqa and Nawaz, Raheel ORCID: https://orcid.org/0000-0001-9588-0052 (2021) HateClassify: A Service Framework for Hate Speech Identication on Social Media. IEEE Internet Computing, 25 (1). pp. 40-49. ISSN 1089-7801

Preview

Accepted Version Available under License In Copyright. Download (1MB) | Preview

Abstract

It is indeed a challenge for the existing machine learning approaches to segregate the hateful content from the one that is merely offensive. One prevalent reason for low accuracy of hate detection with the current methodologies is that these techniques treat hate classification as a multi-class problem. In this work, we present the hate identification on the social media as a multi-label problem. To this end, we propose a CNN-based service framework called "HateClassify" for labeling the social media contents as the hate speech, offensive, or non-offensive. Results demonstrate that the multi-class classification accuracy for the CNN based approaches particularly Sequential CNN (SCNN) is competitive and even higher than certain state-of-the-art classifiers. Moreover, in the multi-label classification problem, sufficiently high performance is exhibited by the SCNN among other CNN-based techniques. The results have shown that using multi-label classification instead of multi-class classification, hate speech detection is increased up to 20%.