Decoding Fake Narratives in Spreading Hateful Stories: A Dual-Head RoBERTa Model with Multi-Task Learning

TL;DR

This paper presents a dual-head RoBERTa model with multi-task learning to detect fake hate speech narratives in code-mixed Hindi-English social media texts, addressing classification, target, and severity prediction tasks.

Contribution

The study introduces a novel multi-task learning approach with a dual-head RoBERTa model for detecting fake hate narratives in code-mixed social media data, advancing NLP techniques for harmful content detection.

Findings

Achieved competitive results on the Faux-Hate shared task.

Demonstrated effectiveness of multi-task learning for hate speech detection.

Enhanced performance through domain-specific pretraining.

Abstract

Social media platforms, while enabling global connectivity, have become hubs for the rapid spread of harmful content, including hate speech and fake narratives \cite{davidson2017automated, shu2017fake}. The Faux-Hate shared task focuses on detecting a specific phenomenon: the generation of hate speech driven by fake narratives, termed Faux-Hate. Participants are challenged to identify such instances in code-mixed Hindi-English social media text. This paper describes our system developed for the shared task, addressing two primary sub-tasks: (a) Binary Faux-Hate detection, involving fake and hate speech classification, and (b) Target and Severity prediction, categorizing the intended target and severity of hateful content. Our approach combines advanced natural language processing techniques with domain-specific pretraining to enhance performance across both tasks. The system achieved competitive results, demonstrating the efficacy of leveraging multi-task learning for this complex problem.