BanglaShop-CRS: A User-Centric Bangla Dataset for Conversational Recommendation
Abstract
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 (κ=0.65) and comparable human and GPT-5.1 judgments. BanglaShop-CRS provides a scalable benchmark for advancing conversational recommendation in Bangla.
Related
- chATLAS: A Retrieval-Augmented Conversational Assistant for the ATLAS Experiment
- Reducing quantum and classical resources for quantum-centric supercomputing workloads on near-term hardware
- Recommendation Feedback Loops Shape Urban Income Segregation and Venue Visitation
- Analyzing Initialization Strategies for the Local Unitary Cluster Jastrow Ansatz within the Quantum-Centric Supercomputing Framework
- Recoverable Quantum Computation: An Information-Centric Paradigm for Quantum Computing with Errors
BibTeX
@misc{prama2026banglashopcrs,
title = {{BanglaShop-CRS: A User-Centric Bangla Dataset for Conversational Recommendation}},
author = {Tabia Tanzin Prama and Christopher M. Danforth and Peter Sheridan Dodds},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.18715},
eprint = {2609.18715},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.18715},
}
RIS
TY - UNPB
TI - BanglaShop-CRS: A User-Centric Bangla Dataset for Conversational Recommendation
AU - Tabia Tanzin Prama
AU - Christopher M. Danforth
AU - Peter Sheridan Dodds
PY - 2026
DA - 2026/09/16
PB - arXiv
DO - 10.48550/arxiv.2609.18715
UR - https://arxiv.org/abs/2609.18715
AB - 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 (κ=0.65) and comparable human and GPT-5.1 judgments. BanglaShop-CRS provides a scalable benchmark for advancing conversational recommendation in Bangla.
ER -