Implementation of Machine Learning for Student Sentiment Analysis as a Basis for Evaluating the Quality of Educational Services at Private Higher Education Institutions in Padang Lawas
DOI:
https://doi.org/10.30865/jurikom.v15i5.10214Keywords:
Machine Learning, Sentiment Analysis, Student Feedback, Educational Service Quality, Higher EducationAbstract
The quality of educational services is an important factor in improving student satisfaction and institutional competitiveness in higher education. Student opinions and experiences provide valuable information for evaluating the effectiveness of academic and non-academic services. However, student feedback is often collected and analyzed manually, making it difficult to identify sentiment patterns and extract meaningful insights efficiently. This study aims to analyze student sentiment regarding the quality of educational services at private higher education institutions in Padang Lawas using machine learning techniques. The research focuses on classifying student opinions into positive, negative, and neutral sentiments to identify perceptions of educational services. The research stages include data collection from student reviews and feedback, text preprocessing, feature extraction, sentiment classification, and model evaluation. Machine learning algorithms will be applied to classify sentiment, while performance will be measured using accuracy, precision, recall, and F1-score. The results are expected to provide an overview of student perceptions of educational services and identify aspects that require improvement. Furthermore, the findings are expected to support data-driven decision-making in evaluating service quality, improving academic administration, and developing student-centered educational policies. This study is expected to contribute to the application of machine learning in higher education evaluation and provide practical recommendations for improving educational service quality at private higher education institutions in Padang Lawas.
References
[1] J. Ilmiah, E. & Erudisi, A. Zahara, M. I. Kabullah, and R. E. Putera, “JIEE: Effectiveness of the OSSRBA (Online Single Submission Risk Based Approach) System in Business Licensing Services in Payakumbuh City DPMPTSP,” vol. 3, pp. 22–40, 2023.
[2] M. Overton, S. Larson, L. J. Carlson, and S. Kleinschmit, “Public data primacy: the changing landscape of public service delivery as big data gets bigger,” Global Public Policy and Governance, vol. 2, no. 4, pp. 381–399, Dec. 2022, doi: 10.1007/s43508-022-00052-z.
[3] W. Jin, “Challenges and Innovative Countermeasures Faced by Public Administration in the Context of Big Data and Internet of Things,” Math. Probl. Eng., vol. 2022, 2022, doi: 10.1155/2022/8949365.
[4] M. S. Novelan, S. Efendi, P. Sihombing, and H. Mawengkang, “VEHICLE ROUTING PROBLEM OPTIMIZATION WITH MACHINE LEARNING IN IMBALANCED CLASSIFICATION VEHICLE ROUTE DATA,” Eastern-European Journal of Enterprise Technologies, vol. 5, no. 3(125), pp. 49–56, 2023, doi: 10.15587/1729-4061.2023.288280.
[5] M. S. Novelan and S. Aryza, “OPTIMIZATION CVRP WITH MACHINE LEARNING FOR IMPROVED CLASSIFICATION OF IMBALANCED DATA FOOD DISTRIBUTION,” JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), vol. 10, no. 4, pp. 917–925, Jun. 2025, doi: 10.33480/jitk.v10i4.6467.
[6] A. Rejeb et al., “The Internet of Things (IoT) in healthcare: Taking stock and moving forward,” Jul. 01, 2023, Elsevier B.V. doi: 10.1016/j.iot.2023.100721.
[7] H. W. Dhany, F. Izhari, and S. Komputer, “Jurnal ICT : Information and Communication Technologies, 15 (2) (2024) 48-54 Prediction analysis condition animal use algorithm (SVM+KNN),” 2024. [Online]. Available: www.ejournal.marqchainstitute.or.id/index.php/JICT
[8] J. Asharf, N. Moustafa, H. Khurshid, E. Debie, W. Haider, and A. Wahab, “A review of intrusion detection systems using machine and deep learning in internet of things: Challenges, solutions and future directions,” Jul. 01, 2020, MDPI AG. doi: 10.3390/electronics9071177.
[9] K. Khairul, A. H. Nasyuha, A. Ikhwan, M. H. Aly, and A. Ahyanuardi, “Implementation of Multiple Linear Regression to Estimate Profit on Sales of Screen Printing Equipment,” JURNAL INFOTEL, vol. 15, no. 2, pp. 55–61, Jun. 2023, doi: 10.20895/infotel.v15i2.934.
[10] B. Kaur et al., “Internet of Things (IoT) security dataset evolution: Challenges and future directions,” Jul. 01, 2023, Elsevier B.V. doi: 10.1016/j.iot.2023.100780.
[11] R. Farta Wijaya, F. Kurniawan, R. R. Putrai, A. Alvin, F. Sains, and D. Teknologi, “OPTIMIZING THE MANAGEMENT OF VILLAGE ACTIVITIES THROUGH INFORMATION SYSTEMS FOR TRANSPARENCY AND ACCOUNTABILITY IN PERTUMBUKAN VILLAGE, WAMPU DISTRICT,” 2024.
[12] M. S. Hamid, A. Eviyanti, H. Hindarto, and N. Ariyanti, “Analisis Sentimen Tingkat Kepuasan Aplikasi WordPress Menggunakan Metode K-Nearest Neighbor dan Naive Bayes,” SMATIKA JURNAL, vol. 15, no. 01, pp. 102–114, Jun. 2025, doi: 10.32664/smatika.v15i01.1522.
[13] A. Putera Utama Siahaan, N. Azizah Harahap, R. Yuni Simanullang, and P. Wanny, “Analysis of Inpatient Data Using Cluster Analysis on Simulation Dataset,” Bulletin of Information Technology (BIT), vol. 6, no. 1, pp. 33–39, 2025, doi: 10.47065/bit.v5i2.1830.
[14] A. T. Talmera, M. Wardhana, and V. Ratnasari, “Analysis of the Impact of UI/UX Elements on User Satisfaction and Loyalty In E-Commerce Platforms: An Empirical Study on the Tokopedia Platform,” Journal of Social Research, 2025, [Online]. Available: http://ijsr.internationaljournallabs.com/index.php/ijsr
[15] M. Iqbal and S. Efendi, “Data-Driven Approach for Credit Risk Analysis Using C4.5 Algorithm,” ComTech: Computer, Mathematics and Engineering Applications, vol. 14, no. 1, pp. 11–20, May 2023, doi: 10.21512/comtech.v14i1.8243.
[16] A. Alamsyah and F. Saviera, “A Comparison of Indonesia’s E-Commerce Sentiment Analysis for Marketing Intelligence Effort (case study of Bukalapak, Tokopedia and Elevenia),” 2021.
