BARD10: A New Benchmark Reveals Significance of Bangla Stop-Words in Authorship Attribution

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Moosa, Abdullah Muhammad, Sultana, Nusrat, Moosa, Mahdi Muhammad, Hossain, Md. Miraiz
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917073098113024
author Moosa, Abdullah Muhammad
Sultana, Nusrat
Moosa, Mahdi Muhammad
Hossain, Md. Miraiz
author_facet Moosa, Abdullah Muhammad
Sultana, Nusrat
Moosa, Mahdi Muhammad
Hossain, Md. Miraiz
contents This research presents a comprehensive investigation into Bangla authorship attribution, introducing a new balanced benchmark corpus BARD10 (Bangla Authorship Recognition Dataset of 10 authors) and systematically analyzing the impact of stop-word removal across classical and deep learning models to uncover the stylistic significance of Bangla stop-words. BARD10 is a curated corpus of Bangla blog and opinion prose from ten contemporary authors, alongside the methodical assessment of four representative classifiers: SVM (Support Vector Machine), Bangla BERT (Bidirectional Encoder Representations from Transformers), XGBoost, and a MLP (Multilayer Perception), utilizing uniform preprocessing on both BARD10 and the benchmark corpora BAAD16 (Bangla Authorship Attribution Dataset of 16 authors). In all datasets, the classical TF-IDF + SVM baseline outperformed, attaining a macro-F1 score of 0.997 on BAAD16 and 0.921 on BARD10, while Bangla BERT lagged by as much as five points. This study reveals that BARD10 authors are highly sensitive to stop-word pruning, while BAAD16 authors remain comparatively robust highlighting genre-dependent reliance on stop-word signatures. Error analysis revealed that high frequency components transmit authorial signatures that are diminished or reduced by transformer models. Three insights are identified: Bangla stop-words serve as essential stylistic indicators; finely calibrated ML models prove effective within short-text limitations; and BARD10 connects formal literature with contemporary web dialogue, offering a reproducible benchmark for future long-context or domain-adapted transformers.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08085
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BARD10: A New Benchmark Reveals Significance of Bangla Stop-Words in Authorship Attribution
Moosa, Abdullah Muhammad
Sultana, Nusrat
Moosa, Mahdi Muhammad
Hossain, Md. Miraiz
Computation and Language
Artificial Intelligence
This research presents a comprehensive investigation into Bangla authorship attribution, introducing a new balanced benchmark corpus BARD10 (Bangla Authorship Recognition Dataset of 10 authors) and systematically analyzing the impact of stop-word removal across classical and deep learning models to uncover the stylistic significance of Bangla stop-words. BARD10 is a curated corpus of Bangla blog and opinion prose from ten contemporary authors, alongside the methodical assessment of four representative classifiers: SVM (Support Vector Machine), Bangla BERT (Bidirectional Encoder Representations from Transformers), XGBoost, and a MLP (Multilayer Perception), utilizing uniform preprocessing on both BARD10 and the benchmark corpora BAAD16 (Bangla Authorship Attribution Dataset of 16 authors). In all datasets, the classical TF-IDF + SVM baseline outperformed, attaining a macro-F1 score of 0.997 on BAAD16 and 0.921 on BARD10, while Bangla BERT lagged by as much as five points. This study reveals that BARD10 authors are highly sensitive to stop-word pruning, while BAAD16 authors remain comparatively robust highlighting genre-dependent reliance on stop-word signatures. Error analysis revealed that high frequency components transmit authorial signatures that are diminished or reduced by transformer models. Three insights are identified: Bangla stop-words serve as essential stylistic indicators; finely calibrated ML models prove effective within short-text limitations; and BARD10 connects formal literature with contemporary web dialogue, offering a reproducible benchmark for future long-context or domain-adapted transformers.
title BARD10: A New Benchmark Reveals Significance of Bangla Stop-Words in Authorship Attribution
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2511.08085