Unraveling Social Perceptions & Behaviors towards Migrants on Twitter

TL;DR

This paper explores social perceptions and behaviors towards migrants on Twitter, identifying key sentiments and actions, and introduces a transformer-based NLP model that improves hate speech detection by distinguishing perceptual and behavioral nuances.

Contribution

It provides a theoretical framework for understanding migrant-related perceptions and behaviors on social media and develops a novel NLP model for nuanced hate speech detection.

Findings

Identified sympathy and antipathy as key perceptions.

Recognized solidarity and animosity as dominant behaviors.

Proposed a BERT + CNN model with 0.76 F1-score for hate speech detection.

Abstract

We draw insights from the social psychology literature to identify two facets of Twitter deliberations about migrants, i.e., perceptions about migrants and behaviors towards mi-grants. Our theoretical anchoring helped us in identifying two prevailing perceptions (i.e., sympathy and antipathy) and two dominant behaviors (i.e., solidarity and animosity) of social media users towards migrants. We have employed unsuper-vised and supervised approaches to identify these perceptions and behaviors. In the domain of applied NLP, our study of-fers a nuanced understanding of migrant-related Twitter de-liberations. Our proposed transformer-based model, i.e., BERT + CNN, has reported an F1-score of 0.76 and outper-formed other models. Additionally, we argue that tweets con-veying antipathy or animosity can be broadly considered hate speech towards migrants, but they are not the same. Thus, our approach has fine-tuned the binary hate speech detection task by highlighting the granular differences between perceptual and behavioral aspects of hate speeches.