Unified and Multilingual Author Profiling for Detecting Haters

TL;DR

This paper introduces a unified multilingual user profiling framework that detects hate speech spreaders across languages using sentence transformers and attention mechanisms, providing explainability and outperforming existing models.

Contribution

The paper proposes a novel multilingual user profiling method with attention-based explainability that surpasses current state-of-the-art transformer models.

Findings

Outperforms existing multilingual transformer models

Provides explainability through attention weights

Effective in identifying hate speech spreaders across languages

Abstract

This paper presents a unified user profiling framework to identify hate speech spreaders by processing their tweets regardless of the language. The framework encodes the tweets with sentence transformers and applies an attention mechanism to select important tweets for learning user profiles. Furthermore, the attention layer helps to explain why a user is a hate speech spreader by producing attention weights at both token and post level. Our proposed model outperformed the state-of-the-art multilingual transformer models.