Performance Analysis of KNN and BERT Algorithms for Classifying Student Sentiments Towards Campus Services
DOI:
https://doi.org/10.30871/jaic.v10i1.11365Keywords:
Sentiment Analysis, KNN, BERT, IndoBERT, Student FeedbackAbstract
This study addresses the limitations of campus service evaluation processes that are still conducted manually and are unable to optimally process students’ textual opinions. The objective of this research is to analyze and compare the performance of the K-Nearest Neighbor (KNN) and BERT algorithms in classifying student sentiments toward campus services. The research stages include text preprocessing, the generation of IndoBERT embeddings for the KNN model, and fine-tuning IndoBERT for direct sentiment classification. The dataset consists of student evaluation texts from the Faculty of Engineering at UNSULBAR, labeled as negative, neutral, and positive sentiments. Model evaluation is performed using accuracy, precision, recall, and F1-score metrics. The results show that the basic KNN model achieves an accuracy of 79%, while KNN with hyperparameter tuning improves performance to 86%. The BERT model delivers the best performance, achieving an accuracy of 88.68%, precision of 87.87%, recall of 90.19%, and an F1-score of 88.79%. These findings indicate that transformer-based approaches, particularly IndoBERT, are more effective in understanding the contextual nuances of student language than traditional methods, and are therefore more recommended for sentiment analysis implementation in campus service evaluation.
Downloads
References
[1] S. Masyita, “Kepuasan Mahasiswa Ditinjau dari Kualitas Pelayanan Akademik dan Non Akademik (Studi pada Program Studi Manajemen STIEM Bongaya),” J. Brand, vol. 2, no. 1, p. 90, 2020, [Online]. Available: https://forlap.ristekdikti.go.id
[2] D. Suranti, Y. Yupianti, and V. N. Sari, “Implementasi Metode Bayes Dalam Evaluasi Kepuasan Mahasiswa Terhadap Layanan Universitas,” SINTECH (Science Inf. Technol. J., vol. 4, no. 1, pp. 12–21, 2021, doi: 10.31598/sintechjournal.v4i1.569.
[3] J. Waruwu, J. Dawolo, D. Laoli, Y. P. Harefa, O. Zebua, and D. C. Lase, “Nias Menggunakan Metode Analisis Regresi,” vol. 4, no. 2, pp. 143–148, 2024.
[4] A. Bulu, E. Umar, and P. M. Ate, “Analisis Sentimen Terhadap Sistem Informasi Akademik STIMIKOM Stella Maris Sumba Menggunakan Algoritma Naïve Bayes,” J. Sist. Inf. Dan Inform., vol. 2, no. 1, pp. 115–124, 2023, doi: 10.47233/jiska.v1i2.1085.
[5] L. R. Dharmawan, I. Arwani, and D. E. Ratnawati, “Analisis Sentimen pada Sosial Media Twitter Terhadap Layanan Sistem Informasi Akademik Mahasiswa Universitas Brawijaya dengan Metode K- Nearest Neighbor,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 4, no. 3, pp. 959–965, 2020, [Online]. Available: http://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/7099
[6] P. Nabila, F. Wajidi, and W. Firgiawan, “Analisis Algoritma K-Nearest Neighbor dan Naive Bayes pada Kebijakan Perkuliahan Online dengan Multi Bahasa,” Techno.Com, vol. 24, no. 2, pp. 524–542, 2025, doi: 10.62411/tc.v24i2.12656.
[7] M. A. Korompot, V. P. Rantung, and ..., “Aplikasi Evaluasi Analisis Sentimen Terhadap Layanan Akademik Menggunakan Algoritma K-Nearest Neighbor Berbasis Web,” … , Educ. …, pp. 18–26, 2024, [Online]. Available: https://jibeit.teknikinformatika.org/index.php/jibeit/article/view/60
[8] B. Wilie et al., “IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding,” 2019.
[9] I. H. Kusuma and N. Cahyono, “Analisis Sentimen Masyarakat Terhadap Penggunaan E-Commerce Menggunakan Algoritma K-Nearest Neighbor,” J. Inform. J. Pengemb. IT, vol. 8, no. 3, pp. 302–307, 2023, doi: 10.30591/jpit.v8i3.5734.
[10] D. A. YULIASARI, “Pengukuran Kepuasan Mahasantri Terhadap Pesantren Mahasiswa Unissula Berbasis Analisis Sentimen Menggunakan Indobert,” Accid. Anal. Prev., 2023.
[11] W. Firgiawan and D. Yustianisa, “Penyetelan Hiperparameter untuk Mengoptimalkan Stunting Klasifikasi dengan Algoritma KNN , SVM , dan Naïve Bayes Machine Translated by Google,” vol. 19, no. 1, pp. 92–104, 2021.
[12] M. I. Fikri, T. S. Sabrila, and Y. Azhar, “Perbandingan Metode Naïve Bayes dan Support Vector Machine pada Analisis Sentimen Twitter,” Smatika J., vol. 10, no. 02, pp. 71–76, 2020, doi: 10.32664/smatika.v10i02.455.
[13] S. P. Collins et al., “No Title 済無No Title No Title No Title,” no. April 2024, pp. 167–186, 2021.
[14] N. Cahyono and Anggista Oktavia Praneswara, “Analisis Sentimen Ulasan Aplikasi TikTok Shop Seller Center di Google Playstore Menggunakan Algoritma Naive Bayes,” Indones. J. Comput. Sci., vol. 12, no. 6, pp. 3925–3940, 2023, doi: 10.33022/ijcs.v12i6.3473.
[15] A. Tantoni, “Ekstraksi Label Otomatis untuk Analisis Sentimen dalam Bahasa Indonesia Teks,” vol. 15, no. 3, pp. 718–728, 2025.
[16] M. Z. Subarkah, M. Hildha, N. T. Amanda, and E. Zukhronah, “Analisis Sentimen Review Tempat Wisata Pada Data Analisis Sentimen Review Tempat Wisata Pada Data Online Travel Agency Di Yogyakarta Menggunakan Model Neural Network IndoBERTweet Fine Tuning (Analysis of Sentiment Reviews of Tourist Attractions on Online ,” Semin. Nas. Off. Stat., vol. 1, no. https://prosiding.stis.ac.id/index.php/semnasoffstat/issue/view/6, pp. 543–552, 2022.
[17] S. Ratnaswari, N. C. Wibowo, D. Satria, and Y. Kartika, “Analisis Sentimen Menggunakan Metode Lexicon-Based Dan Support Vector Machine Pada Presiden Dan Wakil Presiden Indonesia,” vol. 13, no. 1, pp. 362–368, 2025.
[18] P. Studi, S. Informasi, and F. Sains, “Prediksi Produksi Batu Andesit Menggunakan Algoritma Support Vector Regression Prediction Of Andesit Stone Production Using,” vol. 13, pp. 1893–1901, 2024.
[19] Z. A. Sriyanti, D. S. Y. Kartika, and A. R. E. Najaf, “Implementasi Model Bert Pada Analisis Sentimen Pengguna Twitter Terhadap Aksi Boikot Produk Israel,” J. Inform. dan Tek. Elektro Terap., vol. 12, no. 3, pp. 2335–2342, 2024, doi: 10.23960/jitet.v12i3.4743.
[20] A. C. Surya, N. Aurora, A. Satria, and C. T. Nadeak, “Implementasi sentence transformer berbasis bert untuk edukasi dan informasi tentang hiv/aids,” vol. 2, no. 1, pp. 607–614, 2025.
[21] S. Kasus, S. Ransomware, and D. Nasional, “Topic Modelling Berbasis Embedding pada Komentar YouTube,” pp. 873–884, 2024.
[22] Joshua Agung Nurcahyo and Theopilus Bayu Sasongko, “Hyperparameter Tuning Algoritma Supervised Learning untuk Klasifikasi Keluarga Penerima Bantuan Pangan Beras,” Indones. J. Comput. Sci., vol. 12, no. 3, pp. 1351–1365, 2023, doi: 10.33022/ijcs.v12i3.3254.
[23] N. Alvionika, S. Faisal, R. Rahmat, and A. F. N. Masruriyah, “Analisis Sentimen Pada Komentar Instagram Provider By.U Menggunakan Metode K-Nearest Neighbors (KNN),” J. Algoritm., vol. 21, no. 2, pp. 50–63, 2024, doi: 10.33364/algoritma/v.21-2.1672.
[24] P. Studi, T. Informatika, F. Sains, D. A. N. Teknologi, U. Islam, and N. Syarif, “No Title,” 2024.
[25] Y. R. Nasution, A. H. Lubis, and T. F. Eliza, “Analisis Sentimen Platform X Mengenai Pro Kontra Rekrutmen Guru Melalui Marketplace Menggunakan Metode Naïve Bayes,” Bull. Comput. Sci. Res., vol. 4, no. 6, pp. 406–413, 2024, doi: 10.47065/bulletincsr.v4i6.368.
[26] V. A. Permadi, “Analisis Sentimen Menggunakan Algoritma Naive Bayes Terhadap Review Restoran di Singapura,” pp. 141–151.
[27] S. M. Natzir, “Perbandingan Kinerja Model Pembelajaran Mesin dalam Prediksi Banjir menggunakan KNN , Naive Bayes , dan Random Forest,” vol. 14, no. c, pp. 59–64, 2023.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Mutmainna Mutmainna, Heliawati Hamrul, Wawan Firgiawan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
