Hindi-English Hate Speech Detection: Author Profiling, Debiasing, and Practical Perspectives

• DOI: 10.1609/aaai.v34i01.5374
• Publication Date: 2020-06-04T08:19:57Z
• Authors: Shivang Chopra; Ramit Sawhney; Puneet Mathur; Rajiv Ratn Shah
• Keywords: Debiasing; Profiling (computer programming)

Code-switching in linguistically diverse, low resource languages is often semantically complex and lacks sophisticated methodologies that can be applied to real-world data for precisely detecting hate speech. In an attempt bridge this gap, we introduce a three-tier pipeline employs profanity modeling, deep graph embeddings, author profiling retrieve instances of speech Hindi-English code-switched language (Hinglish) on social media platforms like Twitter. Through extensive comparison against several baselines two datasets, demonstrate how targeted embeddings combined with network-based features outperform state the art, both quantitatively qualitatively. Additionally, present expert-in-the-loop algorithm bias elimination proposed model study prevalence performance impact debiasing. Finally, discuss computational, practical, ethical, reproducibility aspects deployment our across Web.