Resolving Review–Rating Inconsistencies with Neural Sentiment Classifiers and LLM-Driven Chatbots in Telecom AI
Abstract
Customer reviews play a key role in exploring products before purchasing. Nevertheless, traditional star ratings between 1 and 5 do not always reflect the true sentiment expressed in the accompanying text, especially in ambiguous cases where an assigned star is 2, 3 or 4. Although, a product itself might be high quality but non-product-related factors such as poor customer service or late delivery leads to inconsistencies and poor ratings. The same applies to positive reviews where a customer did not want to be overly negative and well-rated a product despite it being low quality. This article presents a hybrid AI framework designed to resolve such ambiguities in the IT and Telecom field and the related products – such as mobile devices, Wi-Fi routers and SIM cards – by integrating Neural sentiment classifiers and Large Language Models (LLMs). Our model helps conversational agents (Chatbots) to identify inconsistencies in review-ratings and infer the true product sentiment with increased accuracy.
References
1. Abbasi, A., France, S., Zhang, Z., & Chen, H. (2011). Selecting attributes for sentiment classification using feature relation networks. IEEE Transactions on Knowledge and Data Engineering, 23(3), 447–462. https://doi.org/10.1109/TKDE.2010.110
2. Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., ... & Zhang, Y. (2023). Sparks of Artificial General Intelligence: Early experiments with GPT-4 (arXiv:2303.12712). arXiv. https://arxiv.org/abs/2303.12712
3. Deepanchakkaravarthy, K., & Umarani, S. (2024). Enhancing educational outcomes through natural language processing using sentiment analysis to understand course feedback. In Proceedings of the 13th International Conference on System Modeling & Advancement in Research Trends (SMART) (pp. 643–648). IEEE. https://doi.org/10.1109/SMART63812.2024.10882554
4. Lin, X., Kundu, L., Dick, C., Canaveras Galdon, M. A., Vamaraju, J., Dutta, S., & Raman, V. (2024). A primer on generative AI for telecom: From theory to practice (arXiv:2408.09031). arXiv. https://arxiv.org/abs/2408.09031
5. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need (arXiv:1706.03762). arXiv. https://arxiv.org/abs/1706.03762
6. McKinsey & Company. (2023, August). How generative AI could revitalize profitability for telcos. https://www.mckinsey.com/industries/technology-media-and-telecommunications/our-insights/how-generative-ai-could-revitalize-profitability-for-telcos
7. ScienceDirect. (n.d.). Deep neural network. ScienceDirect Topics. https://www.sciencedirect.com/topics/computer-science/deep-neural-network
8. Wikipedia contributors. (n.d.). Neural network (machine learning). Wikipedia. https://en.wikipedia.org/wiki/Neural_network_(machine_learning)
