Development of an Automated Image and Data Processing System for Client Feedback Analysis: A Case Study of the Laguna State Polytechnic University
DOI:
https://doi.org/10.65141/ject.v3i1.n6Keywords:
automated image and data processing system, feedback, mobile scanning, agile methodology, OCR extractionAbstract
The use of a manual, paper-based process for gathering and analyzing client feedback requires the Management Information Systems (MIS) office to sort, encode, and interpret each form, which often leads to delays, inconsistencies, and a high risk of human error. As feedback volume increases, the manual workflow becomes less efficient and slows an institution’s ability to respond and make timely decisions. To address this, the study developed an automated image and data processing system for client feedback analysis at Laguna State Polytechnic University – San Pablo City Campus (LSPU-SPCC) to improve accuracy and efficiency. Using the Agile methodology, the system was developed through requirement gathering, design, development, and continuous testing. Technologies such as Flutter SDK, Dart SDK, Android Studio/Android SDK, Java, Kotlin, Gradle, Google MLKit, TensorFlow Lite, SyncFusion Widget, Camera Plugin, Image Processing Library, Permission Handler, Path Provider, Share plus OpenFile X, and CSV Library enabled mobile scanning, automated data extraction, sentiment analysis, and Excel report generation. The evaluation involved eight (8) respondents and a dataset of 150 scanned test forms. Quantitative results confirmed reliable system performance, achieving a 96.4% OCR character accuracy rate, a sentiment classification F1-score of 0.91, and an average processing time of 2.5 seconds per form. Furthermore, the ISO/IEC 25010 evaluation yielded an overall weighted mean score of 4.39, indicating a very good software quality. Overall, the system served as a highly effective prototype that enhanced feedback processing, reduced errors, and supported faster decision-making.
References
[1] Abdallah, A., Eberharter, D., Pfister, Z., Jatowt, A. (2024). A survey of recent approaches to form understanding in scanned documents. Artificial Intelligence Review, (57)342, 112–130. https://link.springer.com/article/10.1007/s10462-024-11000-0
[2] Bhimavarapu, U. (2025). Revolutionizing customer support: Business impact analysis of automated models. Artificial Intelligence of Things (AIoT) for Retail and Services Management, 1(2), 195–218. https://doi.org/10.4018/979-8-3693-8512-8.ch007
[3] Biggam, J. (2010). Reducing staff workload and improving student summative and formative feedback through automation: Squaring the circle. International Journal of Teaching and Case Studies, 2(3–4), 276–287. https://doi.org/10.1504/ijtcs.2010.033322
[4] Iqbal, M., Tanveer, A., Ul Haq, H. B., Baig, M. D., & Kosar, A. (2023). Enhancing customer satisfaction in e-commerce: The role of service quality and brand trust. Forum for Economic and Financial Studies, 1(1), 1–14. https://doi.org/10.59400/fefs.v1i1.287
[5] Ha, H. T., & Horák, A. (2022). Information extraction from scanned invoice images using text analysis and layout features. arXiv, 102, 1–16. https://doi.org/10.48550/arXiv.2208.04011
[6] Hwang, W., & Salvendy, G. (2010). Number of people required for usability evaluation: The 10±2 rule. Communications of the ACM, 53(5), 130–133. https://doi.org/10.1145/1735223.1735255
[7] Kapoor, S. (2025). A Java-based system for collecting and analyzing college feedback. Journal of Integrated Engineering Sciences, 1(1), 12–18. https://doi.org/10.63686/jies.v1i1002
[8] Lalit, R., Handa, K., & Sharma, N. (2018). Automated feedback collection and analysis system. International Journal of Distributed Artificial Intelligence, 10(1), 43–53. https://doi.org/10.4018/ijdai.2018010104
[9] Marshanda, A., Harijanto, B., & Rahmad, C. (2024). Implementasi Optical Character Recognition (OCR) untuk meningkatkan akurasi dan kecepatan input data di posyandu. Jurnal Informatika Polinema, 11(1), 45–50. https://doi.org/10.33795/jip.v11i1.6025
[10] Myrta, X. (2025). Analysis and development of data validation tools in financial systems: Case study on data quality in investment funds. Ingenious, 5(2), 152–163. https://doi.org/10.58944/gpev5449
[11] Nielsen, J. (2000, March 19). Why you only need to test with 5 users. Nielsen Norman Group. https://www.nngroup.com/articles/why-you-only-need-to-test-with-5-users/
[12] Permana, I. S., Hidayat, T., & Mahardiko, R. (2020). Mobile phone scanner technology adoption: A comparison analysis. In Proceedings of the International Conference on Information Systems and Technology (ICIST 2020) (pp. 245–261). Atlantis Press. https://doi.org/10.2991/aer.k.211129.071
[13] Shin, H. K. (2012). Purchase information extraction model from scanned invoice document image by classification of invoice table header texts. Journal of Digital Convergence, 10(11), 383–387. https://doi.org/10.14400/jdpm.2012.10.11.383
[14] Uday, M., & Raman, R. K. (2025). A web-based student feedback management system using MERN stack for higher education. International Journal for Research in Applied Science and Engineering Technology, 13(9), 231–241. https://doi.org/10.22214/ijraset.2025.73917
[15] Valencia, E., Staffa, S. J., Aslam, Y., Faraoni, D., DiNardo, J. A., Rangel, S. J., & Nasr, V. G. (2023). Validation of automated data extraction from the electronic medical record to provide a pediatric risk assessment score. Anesthesia & Analgesia, 136(4), 738–744. https://doi.org/10.1213/ane.0000000000006300
