Fine-tuned XLM-RoBERTa achieves 97% accuracy on a new private Bengali crime-comment sentiment dataset, though the claimed edge over prior methods is not based on shared benchmarks.
Abusive comments detection in bangla-english code-mixed and transliterated text,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Understanding Public Perception of Crime in Bangladesh: A Transformer-Based Approach with Explainability
Fine-tuned XLM-RoBERTa achieves 97% accuracy on a new private Bengali crime-comment sentiment dataset, though the claimed edge over prior methods is not based on shared benchmarks.