Article Details
Vol. 2 No. 1 (2026): December
LLM-Driven Sentiment Analysis in Customer Service Dashboards: A Framework for Real-Time Feedback Intelligence
Abstract
Purpose: This study develops and evaluates a conceptual framework for integrating Large Language Model (LLM) driven sentiment analysis into customer service dashboards to enable real-time, emotionally intelligent feedback monitoring. The framework addresses gaps in traditional dashboards that fail to capture contextual and affective dimensions of customer experience.Research.
Methodology: A conceptual and analytical approach synthesizes literature on LLM based sentiment analysis, aspect based opinion mining, customer service automation, and dashboard design. A five-layer integration architecture covering data ingestion, processing, LLM analysis, visualization, and human in the loop is proposed and evaluated for real-time enterprise feedback intelligence.
Results: The framework introduces six capabilities real-time negative trend detection, emotionally weighted ticket prioritization, automated escalation, aspect-based sentiment disaggregation, sentiment-trajectory agent performance evaluation, and predictive customer satisfaction modeling. An LLM output schema defines sentiment polarity, emotion, urgency, service aspect, customer risk, and recommended action. Key challenges, including privacy, bias, hallucination, latency, computational cost, and over-reliance, are discussed.
Conclusions: LLM driven sentiment analysis can transform dashboards into emotionally aware decision-support systems, combining contextual understanding with operational metrics, human oversight, and continuous validation.
Limitations: The framework remains conceptual and untested in live deployments, with implementation feasibility and user acceptance to be empirically examined.
Contributions: This study provides a structured, practitioner oriented framework consolidating NLP, customer experience, and information systems knowledge for multilingual, multichannel service environments.
Keywords
How to Cite
Download Citation
References
- Agua, M., António, N., Carrasco, P., & Rassal, C. (2025). Aspect-based sentiment analysis powered by Large Language Models for enhanced customer insights. Tourism & Management Studies, 21(1), 45-61. https://doi.org/10.18089/tms.20250104 Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., … & Horvitz, E. (2019). Guidelines for human-AI interaction. Paper presented at In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (pp. 1–13). ACM. Bahad, P., Chauhan, D., & Bhar, D. (2025). Real-time sentiment-aware analysis of helpdesk voice calls. Procedia Computer Science, 215, 345-352. https://doi.org/10.1016/j.procs.2025.01.045 Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., … & Amodei, D. (2020). Language models are few-shot learning models. Adv. Neural Information Processing Systems, 33, 1877–1901. Cai, C. J., Winter, S., Steiner, D., Wilcox, L., & Terry, M. (2019). “Hello AI”: Uncovering the onboarding needs of medical practitioners for human–artificial intelligence collaborative decisionmaking. Paper presented at Proceedings of the ACM on Human-Computer Interaction, 3(CSCW), 1–24. Cambria, E., Poria, S., Hazarika, D., & Kwok, K. (2017). SenticNet 5: Discovering conceptual primitives for sentiment analysis using context embeddings. Paper presented at In Proceedings of AAAI 2018 (pp. 1795–1802). Chebrolu, M. (2025). Real?Time Feedback Signal Processing: Transforming Customer Surveys into Actionable Intelligence Through NLP?Driven Architectures. International Journal of Computing and Engineering, 7(8), 63-72. https://doi.org/10.47941/ijce.2942 Crolic, C., Thomaz, F., Hadi, R., & Stephen, A. T. (2022). Emotional cues in chatbot interactions and their effect on customer satisfaction. Journal of Marketing Research, 59(4), 678-695. https://doi.or g/10.1177/00222429211045687 Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Paper presented at In Proceedings of the NAACL-HLT 2019 (pp. 4171–4186). Gregor, S. (2006). The nature of theory in information systems. MIS Quarterly, 30(3), 611-642. http s://doi.org/10.2307/25148742
- Gupta, V., Jain, N., Katariya, P., Kumar, A., Morar, S., Oza, P., … & Varghese, J. (2023). An emotion care model using multimodal textual analysis of COVID-19. Chaos, Solitons & Fractals, 144, 110708. https://doi.org/10.1016/j.chaos.2021.110708 Hu, M., & Liu, B. (2004). Mining and summarizing customer reviews. Paper presented at In Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 168–177). ACM. Hussain, A., & Cambria, E. (2018). Semi-supervised learning for big social data analyses. Neurocomputing, 275, 1662–1673. https://doi.org/10.1016/j.neucom.2017.10.010 IBM. (2024a). How can sentiment analysis be used to improve the customer experience? IBM Think. Retrieved from https://www.ibm.com/think/topics/sentiment-analysis-customer-experience IBM. (2024b). Top customer service metrics you should measure. IBM Think. Retrieved from https:// www.ibm.com/think/insights/customer-service-metrics Jaakkola, E. (2020). Designing conceptual articles: Four approaches. AMS Review, 10(1), 18-26. http s://doi.org/10.1007/s13162-020-00161-0 Liu, B. (2012). Sentiment analysis and opinion mining. Synthesis Lectures on Human Language Technologies, 5(1), 1-167. https://doi.org/10.2200/S00416ED1V01Y201204HLT016 Madabushi, H. T., Kochkina, E., & Castelle, M. (2020). Cost-sensitive BERT for generalizable sentence classification with imbalanced data. Paper presented at In Proceedings of the Second Workshop on NLP for Internet Freedom (pp. 1–8). Mohammed, A. M. K., Ali, G. G. M. N., & Khairunnesa, S. (2025). GSAF: An ML?Based sentiment analytics framework for understanding contemporary public sentiment and trends on key societal issues. Information, 16(4). https://doi.org/10.3390/info16040271 Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., … & Lowe, R. (2022). Training language models to follow instructions using human feedback. Advances in Neural Information Processing Systems, 35, 27730–27744. Pang, B., & Lee, L. (2008). Opinion mining and sentiment analyses. Foundations and Trends in Information Retrieval, 2(1–2), 1–135. https://doi.org/10.1561/1500000011 Taboada, M., Brooke, J., & Armstrong, T. (2020). Sentiment analysis in customer support emails: Using VADER and SVM. Expert Systems with Applications, 148. https://doi.org/10.1016/j.eswa.2 020.113224 Tax, S. S., Brown, S. W., & Chandrashekaran, M. (1998). Customer evaluations of service complaint experiences: Implications for relationship marketing. Journal of Marketing, 62(2), 60-76. https://d oi.org/10.1177/002224299806200205 Thejovathi, M., Hasini, P. V. N. S., Harini, K., Mounika, A., Sai Varshitha, K., Aswitha, K., & Shanthi, D. (2025). Sentiment analysis of incoming calls on helpdesk. Journal of Information Systems Engineering and Management, 10(51). https://doi.org/10.52783/jisem.v10i51s.10617 Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., … & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 59986008. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., … & Zhou, D. (2022). Chain-ofthought prompting elicits reasoning in large-language models. Advances in Neural Information Processing Systems, 35, 24824–24837. Werner, C., Montgomery, L., Dodos, S., Tapuc, G., Sharma, D., & Damian, D. (2020). How angry are your customers? Sentiment analysis of support tickets that escalate. arxiv. https://arxiv.org/abs/201 0.13684 Yadav, A., & Vishwakarma, D. K. (2020). Sentiment analysis using deep learning architectures: A review. Artificial Intelligence Review, 53(6), 4335-4385. https://doi.org/10.1007/s10462-019-0979 4-5
- Zeithaml, V. A., Bitner, M. J., & Gremler, D. D. (2018). Services marketing: Integrating customer focus across the firm (7th ed.). Zhang, W., Deng, Y., Liu, B., Pan, S. J., & Bing, L. (2024). Sentiment analysis in the era of large language models: A reality check. In the Findings of NAACL 2024 (pp. 4403–4423). Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.findings-naacl.278
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.