Automated Text Generation and Response Systems for Multi-Cultural Restaurant Review Management: A Machine Learning Approach to Customer Engagement Optimization
DOI:
https://doi.org/10.14419/xh7kv106Published
26-10-2025Keywords:
Automated Text Generation, Multicultural Customer Service, Restaurant Review Management, Cultural Adaptation, Machine LearningAbstract
This study investigates the effectiveness of automated text generation and response systems in optimizing customer engagement for multicultural restaurant review management. The research addresses the critical challenge of managing online reviews across diverse cultural contexts while maintaining operational efficiency and cultural sensitivity. Using a comprehensive dataset of 1,502 customer reviews from restaurants across seven countries, including France, Italy, Poland, India, Russia, Morocco, and Cuba, this study implements a transformer-based machine learning architecture with culturally adaptive response generation capabilities. The methodology employs multi-stage training combining general language model pre-training with domain-specific fine-tuning, incorporating reinforcement learning techniques optimized for customer satisfaction metrics. The system integrates predictive content generation components designed to proactively address recurring service issues before they escalate to formal complaints. Results demonstrate substantial operational improvements, achieving a 95.1% reduction in response processing time while maintaining customer satisfaction scores within 4.7% of human-generated responses. The cultural adaptation mechanisms proved highly effective, achieving cultural appropriateness scores above 8.2 across all geographic regions, with customer engagement rates ranging from 77.2% to 85.1%. The predictive content generation component successfully reduced recurring complaint themes by up to 40.1% for service speed issues, with systematic improvements documented across all major complaint categories. Cost analysis reveals a 98.8% reduction in operational expenses per response while improving response coverage from 67.3% to 98.7%. The study provides empirical evidence that strategically implemented automated response systems can effectively balance operational efficiency with cultural sensitivity, offering scalable solutions for multicultural hospitality operations. These findings contribute to the growing understanding of artificial intelligence applications in cross-cultural customer service while demonstrating practical frameworks for technology implementation in international restaurant operations.
References
Al‑Sharoufi, H., & Al‑Fadhli, W. S. (2025). Bridging the gap: Pragmatic and cultural challenges in machine translation. International Journal of So-ciety, Culture & Language, Articles in Press. https://doi.org/10.22034/ijscl.2025.2062567.4066
Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., Suh, J., Iqbal, S. T., Bennett, P. N., Inkpen, K., Teevan, J., Kikin-Gil, R., & Horvitz, E. (2019). Guidelines for human-AI interaction. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Sys-tems (Paper 3, pp. 1–13). ACM. https://doi.org/10.1145/3290605.3300233
Anderson, M., & Magruder, J. (2012). Learning from the crowd: Regression discontinuity estimates of the effects of an online review database. The Economic Journal, 122(563), 957–989. https://doi.org/10.1111/j.1468-0297.2012.02512.x
Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., Chen, A., Goldie, A., Mirhoseini, A., McKinnon, C., Chen, C., Olsson, C., Olah, C., Hernandez, D., Drain, D., Ganguli, D., Li, D., Tran-Johnson, E., Perez, E., Kerr, J., Mueller, J., Ladish, J., Landau, J., Ndousse, K., Lu-kosuite, K., Lovitt, L., Sellitto, M., Elhage, N., Schiefer, N., Mercado, N., DasSarma, N., Lasenby, R., Larson, R., Ringer, S., Johnston, S., Kravec, S., El Showk, S., Fort, S., Lanham, T., Telleen-Lawton, T., Conerly, T., Henighan, T., Hume, T., Bowman, S. R., Hatfield-Dodds, Z., Mann, B., Amodei, D., Joseph, N., McCandlish, S., Brown, T., & Kaplan, J. (2022). Constitutional AI: Harmlessness from AI feedback. arXiv. https://doi.org/10.48550/arXiv.2212.08073
Barbieri, F., Camacho-Collados, J., Ronzano, F., Espinosa-Anke, L., Ballesteros, M., Basile, V., Patti, V., & Saggion, H. (2018). SemEval-2018 Task 2: Multilingual emoji prediction. In Proceedings of the 12th International Workshop on Semantic Evaluation (pp. 24–33). https://doi.org/10.18653/v1/S18-1003
Bender, E. M., & Friedman, B. (2018). Data statements for Natural Language Processing: Toward mitigating system bias and enabling better sci-ence. Transactions of the Association for Computational Linguistics, 6, 587–604. https://doi.org/10.1162/tacl_a_00041
Blum-Kulka, S., & Olshtain, E. (1984). Requests and apologies: A cross-cultural study of speech act realization patterns (CCSARP). Applied Lin-guistics, 5(3), 196–213. https://doi.org/10.1093/applin/5.3.196
Branco, A., Parada, D., Silva, M., Mendonça, F., Mostafa, S. S., & Morgado-Dias, F. (2024). Sentiment analysis in Portuguese restaurant reviews: Application of transformer models in edge computing. Electronics, 13(3), 589. https://doi.org/10.3390/electronics13030589
Cheong, B. C. (2024). Transparency and accountability in AI systems: Safeguarding wellbeing in the age of algorithmic decision-making. Frontiers in Human Dynamics, 6, 1421273. https://doi.org/10.3389/fhumd.2024.1421273
Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzmán, F., Grave, E., Ott, M., Zettlemoyer, L., & Stoyanov, V. (2020). Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association for Computational Lin-guistics (pp. 8440–8451). https://doi.org/10.18653/v1/2020.acl-main.747
European Union. (2016). Regulation (EU) 2016/679 of the European Parliament and of the Council of 27 April 2016 (General Data Protection Regulation). Official Journal of the European Union, L 119, 1–88. https://eur-lex.europa.eu/eli/reg/2016/679/oj
Ferrara, E. (2023). Fairness and bias in artificial intelligence: A brief survey of sources, impacts, and mitigation strategies. Sci, 6(1), 3. https://doi.org/10.3390/sci6010003
Gao, J., Galley, M., & Li, L. (2019). Neural approaches to conversational AI. Foundations and Trends in Information Retrieval, 13(3), 127–298. https://doi.org/10.1561/1500000074
Gururangan, S., Marasović, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D., & Smith, N. A. (2020). Don’t stop pretraining: Adapt language models to domains and tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 8342–8360). https://doi.org/10.18653/v1/2020.acl-main.740
Islam, M. S., Kabir, M. N., Ghani, N. A., Zamli, K. Z., Zulkifli, N. S. A., Rahman, M. & M., Moni, M. A.(2024). Challenges and future in deep learning for sentiment analysis: A comprehensive review and a proposed novel hybrid approach. Artificial Intelligence Review, 57, Article 62. https://doi.org/10.1007/s10462-023-10651-9
Khanuja, S., Dandapat, S., Srinivasan, A., Sitaram, S., & Choudhury, M. (2020). GLUECoS: An evaluation benchmark for code-switched NLP. In Proceedings of ACL 2020 (pp. 3575–3585). https://doi.org/10.18653/v1/2020.acl-main.329
Kharismi, A., & Subiyanto, A. (2024). Expressive Speech Act of British and American Culinary Review: A cross-cultural pragmatics study. Lingua Cultura, 18(1), 1–9. https://doi.org/10.21512/lc.v18i1.10669
Kohavi, R., Tang, D., & Xu, Y. (2020). Trustworthy online controlled experiments: A practical guide to A/B testing. Cambridge University Press. https://doi.org/10.1017/9781108653985
Krugmann, J. O., & Hartmann, J. (2024). Sentiment analysis in the age of generative AI. Customer Needs and Solutions, 11, Article 3. https://doi.org/10.1007/s40547-024-00143-4
Langer, M., Baum, K., & Schlicker, N. (2025). Effective human oversight of AI-based systems: A signal detection perspective on the detection of inaccurate and unfair outputs. Minds and Machines, 35(1), Article 1. https://doi.org/10.1007/s11023-024-09701-0
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP. In Advances in Neural Information Processing Systems (NeurIPS 2020). https://doi.org/10.48550/arXiv.2005.11401
Majumder, N., Hazarika, D., Gelbukh, A., Cambria, E., & Poria, S. (2018). Multimodal sentiment analysis using hierarchical fusion with context modeling. Knowledge-Based Systems, 161, 124–133. https://doi.org/10.1016/j.knosys.2018.07.041
Merchant, S. (2025). The role of pragmatics in cross-cultural communication. Advance Social Science Archive Journal, 4(1), 1395–1405. https://doi.org/10.55966/assaj.2025.4.1.081
Miah, M. S. U., Kabir, M. M., Sarwar, T. B., Safran, M., Alfarhood, S., & Mridha, M. F. (2024). A multimodal approach to cross-lingual sentiment analysis with ensemble of transformer and LLM. Scientific Reports, 14, 9603. https://doi.org/10.1038/s41598-024-60210-7
Pareek, A., Saini, K., Kumari, A., & Nikita, K. (2023). Restaurant review sentiment analysis: An automated approach to customer feedback analysis. Tuijin Jishu / Journal of Propulsion Technology, 44(1), 110. https://doi.org/10.52783/tjjpt.v44.i1.2216
Polemi, N., Praça, I., Kioskli, K., & Bécue, A. (2024). Challenges and efforts in managing AI trustworthiness risks: A state of knowledge. Frontiers in Big Data, 7, 1381163. https://doi.org/10.3389/fdata.2024.1381163
Rahman, A., Khan, M. A., Bishnu, K. K., Rozario, U., Ishraq, A., Mridha, M. F., & Aung, Z. (2025). Multilingual sentiment analysis in restaurant reviews using aspect-focused learning. Scientific Reports, 15, 28371. https://doi.org/10.1038/s41598-025-12464-y
Roschk, H., & Gelbrich, K. (2014). Identifying appropriate compensation types for service failures: A meta-analytic and experimental analysis. Journal of Service Research, 17(2), 195–211. https://doi.org/10.1177/1094670513507486
Roschk, H., & Kaiser, S. (2012). The nature of an apology: An experimental study on how to apologize after a service failure. Marketing Letters, 24(3), 293–309. https://doi.org/10.1007/s11002-012-9218-x
Schouten, K., & Frasincar, F. (2016). Survey on aspect-level sentiment analysis. IEEE Transactions on Knowledge and Data Engineering, 28(3), 813–830. https://doi.org/10.1109/TKDE.2015.2485209
Stiennon, N., Ouyang, L., Wu, J., Ziegler, D. M., Lowe, R., Voss, C., Radford, A., Amodei, D., & Christiano, P. F. (2020). Learning to summarize with human feedback. Advances in Neural Information Processing Systems, 33, 3008–3021. (arXiv:2009.01325 https://doi.org/10.48550/arXiv.2009.01325)
Sun, Z., Yu, H., Song, X., Liu, R., Yang, Y., & Zhou, D. (2020). MobileBERT: A compact task-agnostic BERT for resource-limited devices. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020). https://doi.org/10.18653/v1/2020.acl-main.195
Wang, Y., & Chaudhry, A. (2018). When and how managers’ responses to online reviews affect subsequent reviews. Journal of Marketing Research, 55(2), 163–177. https://doi.org/10.1509/jmr.15.0511
Wirtz, J., & Mattila, A. S. (2004). Consumer responses to compensation, speed of recovery and apology after a service failure. International Journal of Service Industry Management, 15(2), 150–166. https://doi.org/10.1108/09564230410532484
Xie, K. L., So, K. K. F., & Wang, W. (2017). Joint effects of management responses and online reviews on hotel financial performance: A data-analytics approach. International Journal of Hospitality Management, 62, 101–110. https://doi.org/10.1016/j.ijhm.2016.12.004
Yao, S., Zhao, J., Yu, D., Park, J. S., Zelikman, E., Han, X., Lin, D., Narasimhan, K., & Cao, Y. (2023). ReAct: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629. https://doi.org/10.48550/arXiv.2210.03629
Yun, J., & Park, J. (2022). The effects of chatbot service recovery with emotion words on customer satisfaction, repurchase intention, and positive word-of-mouth. Frontiers in Psychology, 13, 922503. https://doi.org/10.3389/fpsyg.2022.922503
Żbikowska, A. (2020). Cultural differences in a restaurant’s communication with unsatisfied customers: The case of TripAdvisor. Folia Oeconomica Stetinensia, 20(2), 485–500. https://doi.org/10.2478/foli-2020-0061
Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., & Artzi, Y. (2020). BERTScore: Evaluating text generation with BERT. In Proceedings of ICLR 2020. https://doi.org/10.48550/arXiv.1904.09675
Zhao, Y., Wen, L., Feng, X., Li, R., & Lin, X. (2020). How managerial responses to online reviews affect customer satisfaction: An empirical study based on additional reviews. Journal of Retailing and Consumer Services, 57, 102205. https://doi.org/10.1016/j.jretconser.2020.102205