Keywords:
sentiment analysis
natural language processing
insurance
online discourse
continuous learning

  • Abstract

    The increasing reliance on sentiment analysis within the insurance industry highlights the growing importance of accurately interpreting customer feedback to inform strategic decisions, enhance customer engagement manage risks. However, the dynamic and ever-changing nature of online language poses a to the long-term effectiveness of sentiment analysis models. These models often degrade in accuracy over time because of their inability to adapt to new linguistic patterns, emerging terminology shifts in consumer expression driven by external events, regulatory developments competitive pressures. This study investigates the critical necessity for the continuous adaptation and retraining of sentiment analysis models to maintain relevance and accuracy in the insurance sector. Through a qualitative approach, the research examines key drivers of language evolution, including social discourse, cultural trends  institutional changes. It also explores the implications of outdated sentiment models on business performance, particularly regarding misinterpreting customer sentiment, delayed response to market signals, and reduced risk mitigation capabilities. The findings suggest that continuous retraining mechanisms significantly enhance model performance, improving sentiment classification, deeper customer insights, and more responsive decision-making processes. In addition, adaptive sentiment analysis enables insurers to proactively identify reputational and operational risks, ultimately improving organizational efficiency and resilience. This study concludes that ongoing model adaptation should be a strategic priority for insurance firms seeking to harness the full potential of digital sentiment data. It recommends further research into developing robust, context-aware natural language processing (NLP) models, ethical considerations of automated sentiment monitoring, and tailored application of these systems across various insurance products and services.

  • References

    1. Aditya, C. S. K. (2024). Sentiment analysis regarding the impact of Covid-19 on education in Indonesia with the naïve Bayes classifier. AIP Conference Proceedings, 060022, 19–26. https://doi.org/10.1063/5.0194868
    2. Al-Garadi, M. A., Yang, Y. C., Guo, Y., Kim, S., Love, J. S., Perrone, J., & Sarker, A. (2022). Large-scale social media analysis reveals emotions associated with nonmedical prescription drug use. Health Data Science, 2022, 9851989. https://doi.org/10.34133/2022/9851989
    3. Anderson, A., Pesa, J., Choudhry, Z., Brethenoux, C., Furey, P., Jackson, L., Valleta, L. G., Quijano, L. G., & Lorenzo, A. (2024). Patient perceptions of disease burden and treatment of myasthenia gravis based on sentiment analysis of digital conversations. Scientific Reports, 14(1), 1–11. https://doi.org/10.1038/s41598-024-57825-1
    4. Banerjee, A., & Kumar, S. (2024). Artificial intelligence in healthcare. In Green industrial applications of artificial intelligence and Internet of Things. https://doi.org/10.2174/9789815223255124010007
    5. Becot, F. A., & Inwood, S. M. (2022). Medical economic vulnerability: A next step in expanding the farm resilience scholarship. Agriculture and Human Values, 39(3), 1097–1116. https://doi.org/10.1007/s10460-022-10307-4
    6. Chakravarty, U. K., & Arifuzzaman, S. (2024). Sentiment analysis of tweets on social security and Medicare. Social Network Analysis and Mining, 14(1). https://doi.org/10.1007/s13278-024-01248-3
    7. Chawla, S., Sareen, P., Gupta, S., Joshi, M., & Bajaj, R. (2023). Technology-enabled communication during COVID-19: Analysis of tweets from top ten Indian IT companies using NVIVO. International Journal of Information Technology, 15(4), 2063–2075. https://doi.org/10.1007/s41870-023-01242-6
    8. Chen, X. (2023). Online health communities influence people’s health behaviors in the context of COVID-19. PLOS ONE, 18(4), e0282368. https://doi.org/10.1371/journal.pone.0282368
    9. Chiarello, F., Bonaccorsi, A., & Fantoni, G. (2020). Technical sentiment analysis: Measuring advantages and drawbacks of new products using social media. Computers in Industry, 123, 103299. https://doi.org/10.1016/j.compind.2020.103299
    10. Claus, S., & Stella, M. (2022). Natural language processing and cognitive networks identify UK insurers’ trends in investor day transcripts. Future Internet, 14(10), 291. https://doi.org/10.3390/fi14100291
    11. Dare, C., Vellios, N., Kumar, P., Nayak, R., & van Walbeek, C. (2023). A media analysis of the COVID-19 tobacco sales ban in South Africa. International Journal of Environmental Research and Public Health, 20(18), 6733. https://doi.org/10.3390/ijerph20186733
    12. De Proost, M., Coene, G., Nekkebroeck, J., & Provoost, V. (2022). ‘I feel that injustice is being done to me’: A qualitative study of women’s viewpoints on the (lack of) reimbursement for social egg freezing. BMC Medical Ethics, 23(1), 1–11. https://doi.org/10.1186/s12910-022-00774-z
    13. Denkowska, A., & Wanat, S. (2020). A tail dependence-based MST and their topological indicators in modeling systemic risk in the European insurance sector. Risks, 8(2), 39. https://doi.org/10.3390/risks8020039
    14. Fong, T. H. Y., Sarkani, S., & Fossaceca, J. (2021). Auto defect detection using customer reviews for product recall insurance analysis. Frontiers in Applied Mathematics and Statistics, 7, 632847. https://doi.org/10.3389/fams.2021.632847
    15. Guntuku, S. C., Purtle, J., Meisel, Z. F., Merchant, R. M., & Agarwal, A. (2021). Partisan differences in Twitter language among US legislators during the COVID-19 pandemic: Cross-sectional study. Journal of Medical Internet Research, 23(6), e27300. https://doi.org/10.2196/27300
    16. Hayatin, N., Marthasari, G. I., & Nuraini, L. (2020). Optimization of sentiment analysis for Indonesian presidential election using naïve Bayes and particle swarm optimization. Jurnal Online Informatika, 5(1), 81–88. https://doi.org/10.15575/join.v5i1.558
    17. Helkkula, A., Buoye, A. J., Choi, H., Lee, M. K., Liu, S. Q., & Keiningham, T. L. (2020). Parents’ burdens of service for children with ASD – Implications for service providers. Journal of Service Management, 31(5), 1015–1039. https://doi.org/10.1108/JOSM-01-2020-0011
    18. Hokijuliandy, E., Napitupulu, H., & Firdaniza. (2023). Application of SVM and chi-square feature selection for sentiment analysis of Indonesia’s national health insurance mobile application. Mathematics, 11(17), 3765. https://doi.org/10.3390/math11173765
    19. Hotchkiss, J. T., Ridderman, E., & Bufkin, W. (2023). Development of a model and method for hospice quality assessment from natural language processing (NLP) analysis of online caregiver reviews. Palliative and Supportive Care. https://doi.org/10.1017/S1478951523001001
    20. Kalouguina, V., & Wagner, J. (2023). On the determinants and the role of the payers in the uptake of genetic testing and data sharing in personalized health. Frontiers in Public Health, 11, 920286. https://doi.org/10.3389/fpubh.2023.920286
    21. Kastrati, Z., Imran, A. S., Daudpota, S. M., Memon, M. A., & Kastrati, M. (2023). Soaring energy prices: Understanding public engagement on Twitter using sentiment analysis and topic modeling with transformers. IEEE Access, 11, 3257283. https://doi.org/10.1109/ACCESS.2023.3257283
    22. Kusuma, I. Y., & Suherman, S. (2024). The pulse of long COVID on Twitter: A social network analysis. Archives of Iranian Medicine, 27(1), 36–43. https://doi.org/10.34172/aim.2024.06
    23. McCoy, T. H., Castro, V. M., Cagan, A., Roberson, A. M., Kohane, I. S., & Perlis, R. H. (2015). Sentiment measured in hospital discharge notes is associated with readmission and mortality risk: An electronic health record study. PLOS ONE, 10(8), e0136341. https://doi.org/10.1371/journal.pone.0136341
    24. Minarno, A. E., Kusuma, W. A., & Kurniawan, Y. A. (2021). Human activity recognition for static and dynamic activity using convolutional neural network. Telkomnika, 19(6), 1857–1864. https://doi.org/10.12928/TELKOMNIKA.v19i6.20994
    25. Nitiema, P. (2022). Telehealth before and during the COVID-19 pandemic: Analysis of health care workers’ opinions. Journal of Medical Internet Research, 24(2), e29519. https://doi.org/10.2196/29519
    26. Peng, L., Chen, T., Yang, J., & Cong, G. (2024). Changes in online public opinions associated with various three-child supportive policies in China: Observational study using social media data over time. PLOS ONE, 19(7), e0306698. https://doi.org/10.1371/journal.pone.0306698
    27. Qahar, M. Y. Al, Ruldeviyani, Y., Mukharomah, U. N., Fidyawan, M. A., & Putra, R. (2024). Factor analysis influencing Mobile JKN user experience using sentiment analysis. IAES International Journal of Artificial Intelligence, 13(2), 1782–1793. https://doi.org/10.11591/ijai.v13.i2.pp1782-1793
    28. Rosenstein, E. (2021). Activation, non-take-up, and the sense of entitlement: A Swiss case study of disability policy reforms. Swiss Journal of Sociology, 47(2), 241–260. https://doi.org/10.2478/sjs-2021-0017
    29. Shang, Y., Qian, F., Gao, N., Yang, Q., Guo, Y., & Sun, Y. (2022). The impact of sudden public health events on the insurance companies’ investment returns: Based on the investors’ sentiment perspective. Frontiers in Public Health, 10, 810515. https://doi.org/10.3389/fpubh.2022.810515
    30. Sharma, S., & Jain, A. (2020). Role of sentiment analysis in social media security and analytics. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 10(5), e1366. https://doi.org/10.1002/widm.1366
    31. Snowden, L. R., & Graaf, G. (2023). States’ racial resentment correlates with administrative distancing and lower rates of health plan selection in affordable care act marketplaces: A cross-sectional analysis. BMC Health Services Research, 23(1), 1–9. https://doi.org/10.1186/s12913-023-10252-w
    32. Uncovska, M., Freitag, B., Meister, S., & Fehring, L. (2023). Rating analysis and BERTopic modeling of consumer versus regulated mHealth app reviews in Germany. npj Digital Medicine, 6(1), 1–12. https://doi.org/10.1038/s41746-023-00862-3
    33. Zhou, Y., Yang, W. F. Z., Ma, Y., Wu, Q., Yang, D., Liu, T., & Wu, X. (2021). Doctor-patient relationship in the eyes of medical professionals in China during the COVID-19 pandemic: A cross-sectional study. Frontiers in Psychiatry, 12, 768089. https://doi.org/10.3389/fpsyt.2021.768089
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Copyright (c) 2025 The Authors

How to cite

Hakim, L., Nuryasin, I., & Nugroho, S. (2025). Sentiment analysis in insurance: A systematic review of approaches, techniques, and applications. Multidisciplinary Reviews, 8(10), 2025323. https://doi.org/10.31893/multirev.2025323
Crossref
Scopus
Google Scholar
Europe PMC
  • Article viewed - 172
  • PDF downloaded - 54