Detecting Hateful Content on Social Media

Abstract

Abstract: As humans have identified social media as an indispensable mode of interaction, their evil side seems to have spilled all over the social media platforms. With a humongous number of victims to hatred on the social media, we realized it must be rooted out. We proposed creating a classifier that learns from many a feature including lexical, semantic, syntactic, morphological and contextual features. This paper aims to revolve around employing the aforementioned features to learn the classifier and consequently, observe the performance of the classifier. As employing lexical these features in other classification tasks of opinion mining is observed to perform better, it’s expected to work well with hate detection as well.

Keywords: Social media, Natural Language Processing, Hate Speech, Semantic Features, Supervised Learning

Cite this Article: Aaniya Gouse, Afaq Alam Khan, Detecting Hateful Content on Social Media. Journal of Artificial Intelligence Research & Advances. 2019; 6(3): 25–31p.