DEVELOPMENT OF AN INTELLIGENT SYSTEM FOR AUTOMATIC RESPONSE TO CUSTOMER REVIEWS ON MARKETPLACES WITH USING LLM
The article discusses an approach to the development of an intelligent system designed for automatic responses to customer reviews on marketplaces, utilizing advanced artificial intelligence technologies, specifically large language models (LLMs). The relevance of this work is driven by the growing need for automating customer interactions for e-commerce companies and reducing the time spent processing a large volume of reviews, which requires the application of high-tech solutions. The problem faced by companies is the need to respond quickly and effectively to a large number of reviews, which in a traditional setup demands significant effort from support staff. The methods include data collection and preprocessing, as well as the use of the GPT-4 large language model based on transformer architecture for sentiment analysis and generating personalized responses. The model analyzes the emotional tone of reviews and formulates responses that consider context, tone, and subtext, making communication with customers more natural and effective. The research results demonstrated a significant improvement in customer interaction quality, a reduction in review processing time, and a decrease in operator workload. The conclusions confirm that implementing this system in a company can significantly enhance the quality of customer service.
Dobrovolskii D.S., Oleynikov V.S., Rats E.S. Development of an intelligent system for automatic response to customer reviews on marketplaces with using LLM // Research result. Information technologies. – Т.9, №4, 2024. – P. 74-84. DOI: 10.18413/2518-1092-2024-9-4-0-9
While nobody left any comments to this publication.
You can be first.
1. Bragin A.V., Bakhtizin A. R., Makarov V.L. Large language models of the fourth generation as a new tool in scientific work // Artificial societies Founders: Central Economic and Mathematical Institute of the Russian Academy of Sciences, State Academic University for the Humanities. – 2023. – Vol. 18. – No. 1.
2. Tarasenkov D.A., Alexeeva E.A. Artificial Intelligence in E-Commerce. – 2024.
3. Batishchev A. V. et al. Achieving business goals through the use of NLP // Natural-Humanitarian Studies. – 2023. – No. 6 (50). – Pp. 596-600.
4. Stolyarov A.D., Abramov V.I., Abramov A.V. Generative Artificial Intelligence for Business Model Innovation: Opportunities and Limitations // Beneficium. – 2024. – No. 3 (52). – Pp. 43-51.
5. Krasnov F.V. Using Language Models Based on Transformer Architecture for Understanding Search Queries on E-Commerce Platforms // International Journal of Open Information Technologies. – 2023. – Vol. 11. – No. 9. – Pp. 33-40.
6. Krasnov F.V. Managing Product Diversity in Recommendation Models Based on Attention Mechanism Architecture (Transformers) // International Journal of Open Information Technologies. – 2024. – Vol. 12. – No. 1. – Pp. 68-75.
7. Nikonova E.Z., Korolev R.I. Analysis of Architectural Style REST API // Current Issues of Sustainable Development of Society in the Era of Transformational Processes. – 2023. – Pp. 176-179.
8. Marchenkov A.A. Marketplaces as the Main Trend in E-Commerce // Youth Collection of Scientific Articles "Scientific Aspirations". – 2019. – No. 26. – Pp. 65-67.
9. Nikitina O.V. Statistical Analysis of Consumer Preferences in E-Commerce //Issues of Statistics. – 2015. – No. 6. – Pp. 46-52.
10. Vorona A.A. Application of artificial intelligence technologies: Modern realities and prospects // Scientific Notes of the St. Petersburg Branch of the Russian Customs Academy named after V.B. Bobkov. – 2023. – No. 4 (88). – Pp. 69-73.
11. Vaswani A. Attention is all you need // Advances in Neural Information Processing Systems. – 2017.
12. Ehsan A. et al. RESTful API testing methodologies: Rationale, challenges, and solution directions // Applied Sciences. – 2022. – Т. 12. – №. 9. – P. 4369.
13. Hou X. et al. Large language models for software engineering: A systematic literature review // ACM Transactions on Software Engineering and Methodology. – 2023.
14. Achiam J. et al. Gpt-4 technical report // arXiv preprint arXiv:2303.08774. – 2023.
15. Medhat W., Hassan A., Korashy H. Sentiment analysis algorithms and applications: A survey // Ain Shams engineering journal. – 2014. – Т. 5. – №. 4. – P. 1093-1113.
16. Hirschberg J., Manning C.D. Advances in natural language processing // Science. – 2015. – Т. 349. – №. 6245. – P. 261-266.
17. Roumeliotis K.I., Tselikas N.D. Chatgpt and open-ai models: A preliminary review // Future Internet. – 2023. – Т. 15. – №. 6. – P. 192.
18. Tadelis S. The economics of reputation and feedback systems in e-commerce marketplaces //IEEE Internet Computing. – 2015. – Т. 20. – №. 1. – P. 12-19.
19. Sabree S., Albadrani A. OpenAI as a Tool for Programming Embedded Systems. – 2024.
20. Marvin G. et al. Prompt engineering in large language models // International conference on data intelligence and cognitive informatics. – Singapore: Springer Nature Singapore, 2023. – P. 387-402.
21. Örpek Z., Tural B., Destan Z. The language model revolution: Llm and slm analysis //2024 8th International Artificial Intelligence and Data Processing Symposium (IDAP). – IEEE, 2024. – P. 1-4.
22. Ray P.P. ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope // Internet of Things and Cyber-Physical Systems. – 2023. – Т. 3. – P. 121-154.