Understanding User Dissatisfaction with Penang Smart Parking: An Extended TAM-Based Analysis of App Store Reviews

The Penang Smart Parking (PSP) application was launched in August 2019 to modernise parking management in Penang, Malaysia, through a digital, sensor-based payment system. Despite more than six years of operation and a reported development investment of approximately RM115 million, the application continues to hold an average rating of only 1.8 out of 5 stars on the Google Play Store, reflecting persistent user dissatisfaction. This study investigates the root causes of that dissatisfaction by applying an Extended Technology Acceptance Model (TAM) that combines Perceived Ease of Use (PEOU), Perceived Usefulness (PU), and Perceived Security Risk (PSR) with computational text analysis. A dataset of 3,169 user reviews was analysed using Zero-Shot Text Classification, large language model (LLM)-based key-phrase extraction, and Term Frequency–Inverse Document Frequency (TF-IDF) analysis. The results show that usability problems dominate complaints, with PEOU accounting for 69.7% of all classified issues, driven mainly by application crashes, login failures, and registration errors. Security-related concerns, particularly payments deducted but not recorded and missing account balances, represent 8.8% of complaints and undermine user confidence in the system. PU complaints (5.7%) reveal a gap between user expectations and current functionality, including the absence of parking reminders and transaction receipts. A cross-version comparison indicates that these issues have persisted since the application's earliest releases rather than reflecting temporary resistance to change. The findings suggest that user dissatisfaction is systemic, and the study offers evidence-based recommendations across usability, transaction reliability, and version management. It also demonstrates how LLM-based review analysis can be integrated with an established theoretical framework for the post-adoption evaluation of smart-city applications

Technology Acceptance Model; smart parking; user dissatisfaction; zero-shot text classification; app store reviews.

1. Ahmed, A. B., & Haruna, K. (2025). Enhanced SMS spam detection using Bernoulli Naive Bayes with TF-IDF. FUDMA Journal of Sciences, 9(1), 393–399. [Google Scholar] [Crossref]

2. Alfaridzi, M. I., Syafaah, L., & Lestandy, M. (2022). Emotional text classification using TF-IDF and LSTM. JUITA: Jurnal Informatika, 10(2). [Google Scholar] [Crossref]

3. Almaiah, M. A., Al-Otaibi, S., Shishakly, R., Hassan, L., Lutfi, A., Alrawad, M., Qatawneh, M., & Abu Alghanam, O. (2023). Investigating the role of perceived risk, perceived security and perceived trust on smart m-banking application using SEM. Sustainability, 15(13), 9908. [Google Scholar] [Crossref]

4. Alsaleh, N., Alnanih, R., & Alowidi, N. (2025). Enhancing software usability through LLMs: A prompting and fine-tuning framework for analyzing negative user feedback. Computers, 14(9), 363. [Google Scholar] [Crossref]

5. AlShammari, A. F. (2023). Implementation of keyword extraction using term frequency-inverse document frequency (TF-IDF) in Python. International Journal of Computer Applications, 185(35), 9–13. [Google Scholar] [Crossref]

6. Andrade, C. (2020). The limitations of online surveys. Indian Journal of Psychological Medicine, 42(6), 575–576. [Google Scholar] [Crossref]

7. Asia, D. N. (2020). Almost 50% of Malaysian consumers distrust online payment security. [Google Scholar] [Crossref]

8. Bernama. (2020). CAP suggests two-hour limit for Penang public parking lots. Malay Mail. [Google Scholar] [Crossref]

9. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., & Dhariwal, P. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901. [Google Scholar] [Crossref]

10. Bui, M. P., & Nguyen, M. T. N. (2025). How large language models enhance topic modeling on user-generated content. Journal of Physics: Conference Series, 3114(1), 012011. [Google Scholar] [Crossref]

11. Carmona-Díaz, G., Jiménez-Leal, W., Grisales, M. A., Sripada, C., Amaya, S., Inzlicht, M., & Bermúdez, J. P. (2025). An AI-powered research assistant in the lab: A practical guide for text analysis through iterative collaboration with LLMs. Behavior Research Methods. [Google Scholar] [Crossref]

12. Chan, W. M., & Lee, J. W. C. (2021). 5G connected autonomous vehicle acceptance: The mediating effect of trust in the technology acceptance model. Asian Journal of Business Research, 11(1). [Google Scholar] [Crossref]

13. Chaudhary, M., Jain, C., & Anish, P. R. (2025). Exploring zero-shot app review classification with ChatGPT: Challenges and potential. [Google Scholar] [Crossref]

14. Cronin, P., Coughlan, M., & Ryan, F. (2009). Survey research: Process and limitations. International Journal of Therapy and Rehabilitation, 16(1), 9–15. [Google Scholar] [Crossref]

15. Dasgupta, A., & Yavary Mehr, S. (2024). Enhanced MNB method for SPAM e-mail/SMS text detection using TF-IDF vectorizer. American Journal of Mathematical and Computer Modelling, 9(1). [Google Scholar] [Crossref]

16. Davis, F. D., Bagozzi, R. P., & Warshaw, P. R. (1989). User acceptance of computer technology: A comparison of two theoretical models. Management Science, 35(8), 982–1003. [Google Scholar] [Crossref]

17. Dong, Y., & Itoh, M. (2025). A modification of technology acceptance model for investigating driver-vehicle interaction systems usage. PLOS ONE, 20(4). [Google Scholar] [Crossref]

18. Durango, P. A. A., & Monterola, E. B. (2025). Exploring tech adoption and resistance to new systems at St. Michael’s College, Iligan City. International Journal of Social Science and Human Research, 8(11), 8604–8611. [Google Scholar] [Crossref]

19. Dziak, M. (2024). Technology acceptance model (TAM. EBSCO Research Starters. [Google Scholar] [Crossref]

20. Eftee, S. Y., Khan, M. Y., Noor, R., Mahmud, H., & Hasan, M. K. (2025). Extraction of app problems and its corresponding user action from user review of apps using few-shot learning. SSRN. [Google Scholar] [Crossref]

21. Gantulga, U., Sample, B., & Tugsbat, A. (2022). Predicting RFID adoption towards urban smart mobility in Ulaanbaatar, Mongolia. Asia Marketing Journal, 24(1), 2. [Google Scholar] [Crossref]

22. Google Play. (2026). Google Play Community Post: Posting policy—Google Play Help. https://support.google.com/googleplay/answer/16386215?hl=en [Google Scholar] [Crossref]

23. Jain, V., & Jain, N. (2024). From cash to clicks: A systematic review of digital payment adoption using the ADO framework. SAGE Open, 14(4). [Google Scholar] [Crossref]

24. Jamil, N. S., Ku-Mahamud, K. R., Mohamed Din, A., Ahmad, F., ChePa, N., Wan Ishak, W. H., Din, R., & Ahmad, F. K. (2017). A subject identification method based on term frequency technique. International Journal of Advanced Computer Research, 7(30). [Google Scholar] [Crossref]

25. Khattab, O., Singhvi, A., Maheshwari, P., Zhang, Z., Santhanam, K., Vardhamanan, S., Haq, S., Sharma, A., Joshi, T. T., Moazam, H., Miller, H., Zaharia, M., & Potts, C. (2023). DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines (Version 1). arXiv. https://doi.org/10.48550/ARXIV.2310.03714 [Google Scholar] [Crossref]

26. Kuzman, T., Mozetič, I., & Ljubešić, N. (2023). ChatGPT: Beginning of an end of manual linguistic data annotation? Use case of automatic genre identification. [Google Scholar] [Crossref]

27. Latif, I. S., Saputro, R. E., & Barkah, A. S. (2025). Improvement of Technology Acceptance Model (TAM) with PLS-SEM: A systematic literature review. Journal of Information Systems and Informatics, 7(2), 1376. [Google Scholar] [Crossref]

28. Lemos, F., Alves, V., & Ferraz, F. (2025). Is It Time To Treat Prompts As Code? A Multi-Use Case Study For Prompt Optimization Using DSPy (Version 1). arXiv. https://doi.org/10.48550/ARXIV.2507.03620 [Google Scholar] [Crossref]

29. Lin, C. (2022). Exploring transaction security on consumers’ willingness to use mobile payment by using the Technology Acceptance Model. Applied System Innovation, 5(6), 113. [Google Scholar] [Crossref]

30. Low, Y. Y., & Poh, H. Z. (2018). The determinants of intention to use vehicle parking mobile payment application [[Bachelor’s thesis,]. Universiti Tunku Abdul Rahman. [Google Scholar] [Crossref]

31. Ma, Q., & Liu, L. (2004). The technology acceptance model: A meta-analysis of empirical findings. Journal of Organizational and End User Computing, 16(1), 59–72. [Google Scholar] [Crossref]

32. Mahat, S. A. (2025). Assessing user satisfaction of smart parking payment system in Selangor [[Master’s thesis,]. Universiti Utara Malaysia. [Google Scholar] [Crossref]

33. Merhi, M., Hone, K., & Tarhini, A. (2019). A cross-cultural study of the intention to use mobile banking between Lebanese and British consumers: Extending UTAUT2 with security, privacy and trust. Technology in Society, 59, Article 101151. [Google Scholar] [Crossref]

34. Mervaala, E., & Kousa, I. (2025). Out of context! Managing the limitations of context windows in ChatGPT-4o text analyses. Zenodo. [Google Scholar] [Crossref]

35. Mok, O. (2019). Penang’s RM115m smart parking system hits snag, contractor told to show cause. Malay Mail. [Google Scholar] [Crossref]

36. Mu, Y., Wu, B. P., Thorne, W., Robinson, A., Aletras, N., Scarton, C., Bontcheva, K., & Song, X. (2024). Navigating prompt complexity for zero-shot classification: A study of large language models in computational social science. [Google Scholar] [Crossref]

37. Mustafa, A. A., & Abdulazeez, A. M. (2024). A review of text classification based on ML & data mining algorithms. Indonesian Journal of Computer Science, 13(3), 3896. [Google Scholar] [Crossref]

38. Mutiara, B. (2019, July 26). Penang Smart Parking (PSP) system starts next month. [Google Scholar] [Crossref]

39. Naeem, M. Z., Rustam, F., Mehmood, A., Mui-zzud-din, A., I., & Choi, G. S. (2022). Classification of movie reviews using term frequency-inverse document frequency and optimized machine learning algorithms. PeerJ Computer Science, 8, Article e914. [Google Scholar] [Crossref]

40. Nielbo, K. L., Karsdorp, F., Wevers, M., Lassche, A., Baglini, R. B., Kestemont, M., & Tahmasebi, N. (2024). Quantitative text analysis. Nature Reviews Methods Primers, 4(1), 25. https://doi.org/10.1038/s43586-024-00302-w [Google Scholar] [Crossref]

41. NST. (2024). No one in the driver’s seat: Penang’s parking problem is out of control. https://www.nst.com.my/news/nation/2024/05/1050579/no-one-drivers-seat-penangs-parking-problem-out-control [Google Scholar] [Crossref]

42. Oematan, M. E., Rahayu, S., & Dyah, J. (2024). The effect of perceived usefulness and perceived ease of use on behavioral intention mediated by user satisfaction in e-commerce users. Jurnal Ekonomi, 13(3), 472. [Google Scholar] [Crossref]

43. Peng, G., Clough, P. D., Madden, A., Xing, F., & Zhang, B. (2021). Investigating the usage of IoT-based smart parking services in the Borough of Westminster. Journal of Global Information Management, 29(6). [Google Scholar] [Crossref]

44. Permana, M. E., Ramadhan, H., Budi, I., Santoso, A. B., & Putra, P. K. (2020). Sentiment analysis and topic detection of mobile banking application review. Proceedings of the 2020 International Conference on Informatics and Computational Sciences (ICICoS. [Google Scholar] [Crossref]

45. Said, A. J., & Ismail, A. M. (2025). Trends in natural language processing for text classification: A comprehensive survey. International Journal of Science and Research Archive, 14(2), 1540–1547. [Google Scholar] [Crossref]

46. Saprikis, V., & Vlachopoulou, M. (2021). Mapping mobile payment adoption: Customers’ trends and challenges. International Journal of Business and Management, 16(9), 82. [Google Scholar] [Crossref]

47. Shah, F. A., Sabir, A., Sharma, R., & Pfahl, D. (2024). How Effectively Do LLMs Extract Feature-Sentiment Pairs from App Reviews? (Version 3). arXiv. https://doi.org/10.48550/ARXIV.2409.07162 [Google Scholar] [Crossref]

48. Shi, W., Zheng, W., Yu, J. X., & Cheng, H. (2017). Keyphrase extraction using knowledge graphs. In Lecture Notes in Computer Science (pp. 1–16). Springer. [Google Scholar] [Crossref]

49. Shrestha, S., & Mahmoud, A. (2025). Mobile application review summarization using chain of density prompting. [Google Scholar] [Crossref]

50. Sjarif, N. N. A., Mohd Azmi, N. F., Chuprat, S., Md Sarkan, H., Yahya, Y., & Mohd Sam, S. (2019). SMS spam message detection using term frequency-inverse document frequency and random forest algorithm. Procedia Computer Science, 161, 509–515. [Google Scholar] [Crossref]

51. SUK Pulau Pinang. (2026). Penang Smart Parking—Apps on Google Play. https://play.google.com/store/apps/details?id=com.psp.psppark&hl=en [Google Scholar] [Crossref]

52. Sung, Y. Y., & Kim, S. B. (2019). Topical keyphrase extraction with hierarchical semantic networks. [Google Scholar] [Crossref]

53. Szmigin, I., & Foxall, G. (1998). Three forms of innovation resistance: The case of retail payment methods. Technovation, 18(6/7), 459–468. [Google Scholar] [Crossref]

54. Tchakounté, F., Pagore, A. E. Y., Kamgang, J. C., & Atemkeng, M. (2020). CIAA-RepDroid: A fine-grained and probabilistic reputation scheme of Android apps based on sentiment analysis of reviews. Preprints. [Google Scholar] [Crossref]

55. Ting, C. P., Muniandy, M., & Batumalai, C. (2024). Smart parking mobile app system allocation and navigation. Journal of Engineering Science and Technology, 19(Special Issue on ICIT2022), 40–46. [Google Scholar] [Crossref]

56. Törnberg, P. (2023). How to use large language models for text analysis. [Google Scholar] [Crossref]

57. Tsimenidis, S. (2020). Limitations of deep neural networks: A discussion of G. [Google Scholar] [Crossref]

58. Wang, Y., Wang, W., Chen, Q., Huang, K., Nguyen, A., & De, S. (2024). Zero-shot text classification with knowledge resources under label-fully-unseen setting. Neurocomputing, 610, 128580. [Google Scholar] [Crossref]

59. Wang, Z., Pang, Y., & Lin, Y. (2023). Large language models are zero-shot text classifiers. [Google Scholar] [Crossref]

60. Yang, C., Ye, X., Xie, J., Yan, X., Lu, L., Yang, Z., Wang, T., & Chen, J. (2020). Analyzing drivers’ intention to accept parking app by structural equation model. Journal of Advanced Transportation, 3051283. [Google Scholar] [Crossref]

61. Zhang, K., Zhang, Q., Wang, C.-C., & Jang, J.-S. R. (2025). Comprehensive study on zero-shot text classification using category mapping. IEEE Access, 13, 23526–23546 [Google Scholar] [Crossref]

• Smart Iot Device for Weather And Health
• Merlarchive: A Web-Based Academic Hub for UDM With AI-Powered Natural Language Processing
• Enhanced Social Network Security System: Integrating Biometric Authentication for Improved User Verification and Privacy Protection
• Smart Budget Allocation in Public Policy: A Data-Driven Approach for Equitable Resource Distribution
• Decision Support System for Faculty Selection, Promotion, and Reclassification Using Predictive Analytics