HP-BERT: A Framework for Longitudinal Study of Hinduphobia on Social Media via Language Models

During the COVID-19 pandemic, community tensions intensified, contributing to discriminatory sentiments against various religious groups, including Hindu communities. Large language models (LLMs) have shown promise for natural language processing tasks and social media analysis, enabling longitudinal studies of platforms like X (formerly Twitter).We present a computational framework for analyzing anti-Hindu sentiment (Hinduphobia) during the COVID-19 period, introducing an abuse detection and sentiment analysis approach for longitudinal analysis on X (Twitter). We curate and release a "Hinduphobic COVID-19 X (Twitter) Dataset" containing 8,000 annotated and manually verified tweets. Using this dataset, we develop the Hinduphobic BERT (HP-BERT) model through fine-tuning. HP-BERT achieves 94.72% accuracy, outperforming baseline applications of five transformer models to our specific task. The model incorporates multi-label sentiment analysis capabilities through additional fine-tuning on the "SenWave Dataset". Our analysis encompasses approximately 27.4 million tweets from six countries: Australia, Brazil, India, Indonesia, Japan, and the United Kingdom. Statistical analysis reveals moderate correlations (r = 0.312-0.428) between COVID-19 case increases and Hinduphobic content volume, highlighting how pandemic-related stress may contribute to discriminatory discourse. This study provides evidence of social media-based religious discrimination during a COVID-19 crisis.