Uncovering the Narrative: Revealing Trending Topics of Bangladesh in Global Media Using Topic Modeling.
Students & Supervisors
Student Authors
Supervisors
Abstract
This research explores the media coverage of Bangladesh during the turbulent year 2024 through a comprehensive analysis of Al Jazeera news articles. Employing Latent Dirichlet Allocation (LDA) topic modeling, alongside sentiment analysis and temporal trend analysis, this study investigates how international media portrayed Bangladesh’s socio-political developments, economic challenges, and cultural events. Such analysis is essential given the significant gap in computational studies of media representation of emerging South Asian democracies facing governance transitions. The research integrates documentterm matrices, topic clustering, and Latent Semantic Analysis with advanced visualization techniques, including t-SNE projection and longitudinal trend mapping. Findings identify six distinct thematic clusters: student protest movements, governance transitions, religious minority issues, sports diplomacy, refugee crises, and electoral politics. Sentiment analysis reveals notable fluctuations in reporting tone corresponding to key national events. This research contributes valuable insights into international media framing of Bangladesh during a transformative period, offering a data-driven foundation for understanding how global narratives shape perceptions of the nation’s democratic evolution, policy challenges, and regional significance.
Keywords
Publication Details
- Type of Publication:
- Conference Name: 3rd International Conference on Big Data, IoT and Machine Learning
- Date of Conference: 25/09/2025 - 25/09/2025
- Venue: Dhaka International University, Bangladesh.
- Organizer: Department of CSE and EEE, DIU