Understanding Public Perception of Crime in Bangladesh: A Transformer-Based Approach with Explainability

TL;DR

This paper presents a transformer-based model for classifying public sentiment on crime in Bangladesh using social media comments, achieving high accuracy and providing explainability to support policy decisions.

Contribution

It introduces a new dataset of Bangla social media comments and applies a transformer model with explainability to analyze public perception of crime.

Findings

Achieved 97% classification accuracy on Bangla comments

Demonstrated effectiveness of transformers in low-resource language sentiment analysis

Provided explainability to interpret model decisions

Abstract

In recent years, social media platforms have become prominent spaces for individuals to express their opinions on ongoing events, including criminal incidents. As a result, public sentiment can shift dynamically over time. This study investigates the evolving public perception of crime-related news by classifying user-generated comments into three categories: positive, negative, and neutral. A newly curated dataset comprising 28,528 Bangla-language social media comments was developed for this purpose. We propose a transformer-based model utilizing the XLM-RoBERTa Base architecture, which achieves a classification accuracy of 97%, outperforming existing state-of-the-art methods in Bangla sentiment analysis. To enhance model interpretability, explainable AI technique is employed to identify the most influential features driving sentiment classification. The results underscore the effectiveness of transformer-based models in processing low-resource languages such as Bengali and demonstrate their potential to extract actionable insights that can support public policy formulation and crime prevention strategies.