Deep Learning for Hate Speech Detection: A Personality-based Approach
Kyuhan Lee, Sudha Ram · 2024
A crucial element in the combat against hate speech is the development of efficient algorithms for automatically detecting hate speech. Previous research, however, has primarily neglected important insights from the field of psychology literature, particularly the relationship between personality and hate, resulting in suboptimal performance in hate speech detection. To this end, we propose a novel framework for detecting hate speech focusing on people's personality factors reflected in their writing. Our framework has two components: (i) a knowledge distillation model for fully automating the process of personality inference from text and (ii) a personality-based deep learning model for hate speech detection. Our approach is unique in that it incorporates low-level personality factors, which have been largely neglected in prior literature, into automated hate speech detection and proposes novel deep learning components for fully exploiting the intricate relationship between personality and hate (i.e., intermediate personality factors). The evaluation shows that our model significantly outperforms state-of-the-art baselines. Our study paves the way for future research by incorporating personality aspects into the design of automated hate speech detection. In addition, it offers substantial assistance to online social platforms and governmental authorities facing challenges in effectively moderating hate speech.