Metraipolis › archive › dc_18e46a4e3887

BanglaShop-CRS: A User-Centric Bangla Dataset for Conversational Recommendation — arXiv:2609.18715

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18715
License (as archived)
CC0-1.0
Archived
2026-10-15T17:57:40.087Z
SHA-256 of the archived text
b371659ceefcbc0e61cfc613bd0502cc3ea30c127bb0f90926be6e244bf92f01
Stable URL of this page
https://metraipolis.com/documento/dc_18e46a4e3887

How to cite

BanglaShop-CRS: A User-Centric Bangla Dataset for Conversational Recommendation — arXiv:2609.18715 — arXiv (en), https://arxiv.org/abs/2609.18715 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_18e46a4e3887 (Metraipolis archive dc_18e46a4e3887, sha256 b371659ceefcbc0e61cfc613bd0502cc3ea30c127bb0f90926be6e244bf92f01)
BibTeX
@misc{dc18e46a4e3887,
  title = {BanglaShop-CRS: A User-Centric Bangla Dataset for Conversational Recommendation — arXiv:2609.18715},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18715},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_18e46a4e3887; sha256 b371659ceefcbc0e61cfc613bd0502cc3ea30c127bb0f90926be6e244bf92f01},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18715. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Conversational recommender systems~(CRS) enable users to express preferences, constraints, and feedback through natural language interaction. However, existing CRS resources are concentrated in English and other high-resource languages, leaving Bangla and code-mixed Bangla--English settings underrepresented. To address this gap, we introduce BanglaShop-CRS, a large-scale user-centric synthetic Bangla conversational recommendation dataset grounded in real e-commerce behavior. It contains 27,178 multi-turn dialogues, 274,802 utterances, and 3.6M tokens across 10 product domains. Our generation pipeline incorporates user purchase histories, positive and negative feedback, and review texts to maintain consistency between dialogue content and user preferences. We evaluate BanglaShop-CRS under catalog-constrained and open-vocabulary recommendation protocols. Results show that dialogue context improves recommendation quality, while fine-tuning yields further gains across models. Human evaluation by five native Bangla-speaking annotators confirms the fluency, informativeness, logicality, and coherence of the dialogues, with significant agreement across all dimensions. Factual-grounding evaluation further shows stronger alignment with correct than shuffled user records, with substantial inter-annotator agreement ($\kappa=0.65$) and comparable human and GPT-5.1 judgments. BanglaShop-CRS provides a scalable benchmark for advancing conversational recommendation in Bangla.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-09-17 in physics.soc-ph).
Categorie arXiv: Physics and Society (physics.soc-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.18715 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T17:11:39.457Z dalla pagina https://arxiv.org/catchup/physics.soc-ph/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).