← Back to Publications List

ProtestPulseBD: Identifying Social Movement Dynamics in Bangladesh through Topic Modeling and Temporal Sentiment Shifts on Social Media

Students & Supervisors

Student Authors
Mahin Montasir Afif
Bachelor of Science in Computer Science & Engineering, FST
Abdullah Al Noman
Bachelor of Science in Computer Science & Engineering, FST
Arizit Chaki Artha
Bachelor of Science in Computer Science & Engineering, FST
Supervisors
Md. Mortuza Ahmmed
Associate Professor, Faculty, FST

Abstract

In an era of rapidly evolving political climates, especially within digitally active societies, there is a growing demand for high quality datasets and methodologies that enable robust political sentiment analysis. This paper presents ProtestPulseBD, a novel English-language social media dataset and analytical framework developed to examine public sentiment during the recent Bangladesh student-led reform movement. This movement, which began as a focused campaign for specific demands, rapidly evolved into a broader anti-government protest, exemplifying dynamic shifts in public opinion. The dataset consists of social media posts and comments collected across three critical phases: before the movement (pre-July), during the initial reform protests (July1–16), and during the subsequent escalation (July 17–August 5). Using transformer-based models, specifically BERT for sentiment classification and BERTopic for topic modeling, we analyze how public discourse evolved temporally across these phases. Our findings reveal a distinct shift in sentiment and narrative from neutral or reform-focused commentary to increasingly polarized and politically charged expressions. By linking these digital discourse patterns to broader implications for sustainable governance and civic engagement, this study introduces a scalable methodology for political sentiment analysis in low-resource, movement-driven environments. The ProtestPulseBD corpus and analytical pipeline aim to support future research in computational social science, digital civic participation, and evidence-based strategies for inclusive and sustainable governance in urban contexts.

Keywords

Political sentiment analysis· sustainable governance · topic modeling · BERT · ProtestPulseBD

Publication Details

  • Type of Publication:
  • Conference Name: 4th International Conference on Data Analytics and Insights (ICDAI-2026)
  • Date of Conference: 30/07/2026 - 30/07/2026
  • Venue: Techno International New Town, Block- DG 1/1, Action Area 1, New Town, Kolkata-700156
  • Organizer: Techno International New Town
View on Publisher