Does AI-based sentiment analysis predict consumer purchasing behavior in subscription services?
DOI:
https://doi.org/10.61173/mx0mkx74Keywords:
Artificial Intelligence, Sentiment Analysis, Consumer Churn, Subscription Economy, Logistic Regression, Natural Language Processing, Predictive ModellingAbstract
This essay investigates the use of AI-written text sentiment analysis as a predictor of consumer churn in the digital streaming economy. The authors employed over 210,000 records of users of Netflix to generate the primary sentiment scores of the raw reviews left by the user by implementing a Natural Language Processing (NLP) algorithm. These were then inputted into a Logistic Regression model that predicted binary cancellation possibilities. Despite the fact that preliminary values of the Weight of Evidence (WOE) factor have allowed establishing a mathematical relationship between the presence of extremely negative mood and subscription termination, the predictive factor has a final Area Under the Curve (AUC) prediction of 0.4944, which is analogous to a shot in the dark. The extremely low Total Information Value (0.0014) demonstrates that the human behaviour in purchasing is highly multidimensional. It is discovered that, as much as sentiment analysis is applied in the establishment of the overall brand health, text sentiment cannot be applied mathematically to engineer a commercially viable churn prediction system without integrating with other behavioral metrics.
References
Chapman, H. (2023). Netflix Password Sharing Crackdown: Impact on Customer Churn and Loyalty. Insights by Infegy. https://www.infegy.com/insight-brief/the-cost-of-netflixscrackdown Dhivya, S., Ansari, Z., Garg, A., Kalhapure, B., Babasaheb,
Sharma, S., & Shah, M. (2025). The Psychology of Subscription Models: Exploring Consumer Retention and Value Perception in the Digital Economy. Advances in Consumer Research, 2(4), 2675-2683. https://www.researchgate.net/ publication/395358047_The_Psychology_of_Subscription_ Models_Exploring_Consumer_Retention_and_Value_ Perception_in_the_Digital_Economy
Digital Content Next. (2025). Price fatigue fuels shift to bundled, Ad-backed streaming. Digital Content Next. https:// digitalcontentnext.org/blog/2025/08/19/price-fatigue-fuels-shiftto-bundled-ad-backed-streaming/
Eisenstein, S., Bohne, M., & Volodarsky, M. (2024). Combating Subscription Fatigue: A Data-Driven Approach for Streamers. Berkeley Research Group (BRG). h t t p s : / / m e d i a . t h i n k b r g . c o m / w p - c o n t e n t / uploads/2024/10/23152459/CF_Subscription-Fatigue- Streamers_October2024.pdf
Longo, C. (2021). An Analysis of Choice Overload Effects on the User Experience of Subscription-based Streaming Services (Master's Thesis). Copenhagen Business School. https://research.cbs.dk/en/studentProjects/an-analysis-of-choiceoverload-effects-on-the-user-experience-of-/
Martin, D. (1977). Early Warning of Bank Failure: A Logit Regression Approach. Journal of Banking & Finance, 1(3), 249- 276. h t t p s : / / w w w. s c i e n c e d i r e c t . c o m / s c i e n c e / a r t i c l e / pii/037842667790022X
Nguyen, D. (2025). Subscription Fatigue: Analyzing Financial Behavior in a Saturated Subscription Market (Degree Thesis). Arcada University of Applied Sciences: International Business, Financial Management. https://www.theseus.fi/bitstream/10024/891649/2/Nguyen_ Dang.pdf
Nguyen, M. D. (2025). Algorithmic Curation and Consumer Loyalty: A Longitudinal Analysis of Personalization Effects on User Engagement and Subscription Retention in Vietnam's Digital Streaming Platforms. Journal of Economics, Finance and Management Studies, 8(08), 5179-5191. https://doi. org/10.47191/jefms/v8-i8-13
Ohlson, J. A. (1980). Financial Ratios and the Probabilistic Prediction of Bankruptcy. Journal of Accounting Research, 18(1), 109-131. https://www.jstor.org/stable/2490395
Srivastava, R. K., Joshi, N., Muley, P., & Sharma, B. (2025). Assessing User Behaviour Toward Annual Subscription Purchases: A Netflix Case Study. Advances in Consumer Research, 2(4), 4260-4273. https://acr-journal.com/article/assessing-user-behaviour-towardannual-subscription-purchases-a-netflix-case-study-1525/
Sunori, Mittal, & Gangola. (2024). Statistical Analysis of Subscription Fatigue: A Growing Consumer Phenomenon. Proceedings of the third International Conference on Optimisation Techniques in the Field of Engineering (ICOFE–2024). https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5076118
Tanuwijaya, S., Alamsyah, A., & Ariyanti, M. (2021). Mobile customer behaviour predictive analysis for targeting Netflix potential customer. 2021 9th International Conference on Information and Communication Technology (ICoICT), 348-352. IEEE. https://ieeexplore.ieee.org/abstract/document/9527487/ Dean&Francis Fu Su Appendix A Dean&Francis ISSN 2959-6130 Appendix B Dean&Francis Fu Su Dean&Francis ISSN 2959-6130 Dean&Francis Fu Su Dean&Francis ISSN 2959-6130 Dean&Francis Fu Su Dean&Francis ISSN 2959-6130
Downloads
Published
Issue
Section
License
Copyright (c) 2026 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
