Transformer models improve rhetorical detection in Bangla political speeches
BanglaRhet: Benchmarking Classical and Transformer Models for Rhetorical and Persuasion Detection in Bangla Political Speech
Computation and Language
Summary
Political speeches often use special language tricks to persuade listeners. The paper studies how well computer models can recognize these tricks in Bangla language speeches. Using a large collection of Bangla political speech examples, the authors tested several transformer-based AI models and found one called BanglaBERT worked best. The study shows the difficulty of telling apart similar language techniques and suggests more complex approaches are needed.
What this means in practice
- •For social media monitoring teams: Detect persuasive and rhetorical techniques in Bangla political messages to analyze public discourse trends more accurately.
- •For language technology developers: Build language models specialized in recognizing nuanced rhetorical and persuasion techniques in low-resource languages like Bangla.
Authors
Rohit Kumar Sen, Anik Chowdhury
Abstract
Political discourse often uses rhetorical and persuasive language to frame narratives, influence public opinion, and mobilize audiences. While Bangla natural language processing has made progress in sentiment analysis and opinion mining, systematic benchmarking of transformer models for fine-grained rhetorical and persuasion technique detection in Bangla political speech remains largely underexplored. This paper presents a benchmark study of transformer-based models for detecting rhetorical form and persuasive intent in Bangla political discourse. Using BanglaRhet, a manually annotated corpus of 30,289 Bangla political speech segments collected from publicly available political news sources, we formulate two supervised single-label classification tasks: rhetorical technique detection (contrast, repetition, exaggeration, metaphor, rhetorical questions) and persuasion technique detection (blame assignment, call to action, unity call, moral, emotional, and logical appeals). We evaluate four transformer-based models, BanglaBERT, BanglaBERT-Base, SahajBERT, and XLM-RoBERTa-Base, against classical TF-IDF baselines. BanglaBERT achieves the highest performance, with 65.40% macro-F1 for rhetorical technique detection and 66.46% for persuasion technique detection, outperforming the best tuned classical baseline by 19.2 and 13.8 macro-F1 points, respectively. Class-level analysis indicates that errors are mainly associated with semantic overlap among labels, figurative language, and class imbalance. The results provide initial benchmark baselines for Bangla rhetorical and persuasion-aware political discourse analysis and highlight the need for context-aware and multi-label modeling.