Implementasi LDA, TF-IDF, dan BERT dalam Sistem Rekomendasi Dosen Pembimbing untuk Mahasiswa
-
Mutiara Syabilla
*
Universitas Dian Nuswantoro, Semarang,
Indonesia
- Junta Zeniarja Universitas Dian Nuswantoro, Semarang, Indonesia
- Qotrunnada Nabila Universitas Dian Nuswantoro, Semarang, Indonesia (*) Corresponding Author
Abstract
The selection of thesis supervisors is often done manually, which tends to be time-consuming in matching students' research topics with the expertise of faculty members. This study develops a thesis supervisor recommendation system based on the title and abstract of students' final projects, integrating Latent Dirichlet Allocation (LDA), Term Frequency-Inverse Document Frequency (TF-IDF), and Bidirectional Encoder Representations from Transformers (BERT). The research dataset includes 1,096 records from 71 faculty members in the Informatics Engineering Department at Universitas Dian Nuswantoro, collected through Google Scholar. The analysis process begins with text preprocessing such as case folding, tokenization, and stemming, followed by topic analysis using LDA, term-specific weighting through TF-IDF, and context-rich vector representation using BERT. The model matches students' research topics with faculty expertise using Cosine Similarity. Evaluation results show an accuracy of 80%, precision of 66%, and recall of 19%, indicating that the model can provide accurate recommendations, though some relevant items are still missed. This model proves effective in facilitating the selection of thesis supervisors. This research is expected to assist students in finding suitable supervisors and help faculty members identify students with relevant research interests.
Downloads
References
R. Megawati and M. Damayanti, “Peran Dosen Pembimbing Skripsi dalam Proses Penyelesaian Tugas Akhir Mahasiswa,” Journal of Health, Education, Economics, Science, and Technology (J-HEST) , vol. 4, pp. 33–39, 2021
R. Ario Nugroho, “Analisa Penentuan Dosen Pembimbing Tugas Akhir Mahasiswa Menggunakan Naive Bayes Classifier,” Jurnal SIMTIKA, vol. 4, no. 3, 2021.
N. Andriani and B. Wibawanta, “Peran Dosen Pembimbing Sebagai Pemimpin Yang Melayani Dalam Pembimbingan Tugas Akhir Mahasiswa Program Sarjana [The Role Of Supervisor As A Servant Leader In The Final Project Supervision Of Undergraduate Students],” Polyglot: Jurnal Ilmiah, vol. 16, no. 2, pp. 230–251, Jun. 2020, doi: 10.19166/pji.v16i2.1927.
D. Aqmala, I. Farida, A. S. Samasta, and A. Setiawan, “Kompetensi Kinerja Dosen Terhadap Topik Bimbingan Tugas Akhir Mahasiswa Menggunakan Naïve Bayes,” TRANSFORMTIKA, vol. 19, no. 1, pp. 48–56, 2021.
H. Hairani and M. Mujahid, “Recommendations of Thesis Supervisor using the Cosine Similarity Method,” SISTEMASI, vol. 11, no. 3, p. 646, Sep. 2022, doi: 10.32520/stmsi.v11i3.2003.
A. Azhari, E. Buulolo, and N. Silalahi, “Sistem Rekomendasi Dosen Pendamping Skripsi Berbasis Text Rank menggunakan Metode Cosine Similarity,” Pelita Informatika : Informasi dan Informatika, vol. 10, no. 3, pp. 119–122, 2022.
S. Wehnert, V. Sudhi, S. Dureja, L. Kutty, S. Shahania, and E. W. De Luca, “Legal norm retrieval with variations of the bert model combined with TF-IDF vectorization,” in Proceedings of the 18th International Conference on Artificial Intelligence and Law, ICAIL 2021, Association for Computing Machinery, Inc, Jun. 2021, pp. 285–294. doi: 10.1145/3462757.3466104.
J. W. Sun, J. Q. Bao, and L. P. Bu, “Text Classification Algorithm Based on TF-IDF and BERT,” in Proceedings - 2022 11th International Conference of Information and Communication Technology, ICTech 2022, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 533–536. doi: 10.1109/ICTech55460.2022.00112.
N. Yang, J. Jo, M. Jeon, W. Kim, and J. Kang, “Semantic and explainable research-related recommendation system based on semi-supervised methodology using BERT and LDA models,” in Expert Systems with Applications, Elsevier Ltd, Mar. 2022. doi: 10.1016/j.eswa.2021.116209.
Z. Jin, X. Lai, and J. Cao, “Multi-label Sentiment Analysis Base on BERT with modified TF-IDF,” in ISPCE-CN 2020 - IEEE International Symposium on Product Compliance Engineering-Asia 2020, Institute of Electrical and Electronics Engineers Inc., Nov. 2020. doi: 10.1109/ISPCE-CN51288.2020.9321861.
E. Rivadeneira-Pérez and C. Callejas-Hernández, “Leveraging LDA Topic Modeling and BERT Embeddings for Thematic Unsupervised Classification of Tourism News in Rest-Mex Competition,” IberLEF, vol. 1, 2023, [Online]. Available: http://ceur-ws.org
Y. Zhang and L. Zhang, “Movie Recommendation Algorithm Based on Sentiment Analysis and LDA,” in Procedia Computer Scienc2, Elsevier B.V., 2022, pp. 871–878. doi: 10.1016/j.procs.2022.01.109.
P. N. Andono, Sunardi, R. A. Nugroho, and B. Harjo, “Aspect-Based Sentiment Analysis for Hotel Review Using LDA, Semantic Similarity, and BERT,” International Journal of Intelligent Engineering and Systems, vol. 15, no. 5, pp. 232–243, Oct. 2022, doi: 10.22266/ijies2022.1031.21.
D. Jurafsky and J. H. Martin, Speech and Language Processing An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. 2020.
Denis Rothman, Transformers for Natural Language Processing: Build innovative deep neural network architectures for NLP with Python, PyTorch, TensorFlow, BERT, RoBERTa, and more, 2nd ed. Birmingham, Inggris, 2022.
A. Rahmatulloh and R. Gunawan, “Web Scraping with HTML DOM Method for Data Collection of Scientific Articles from Google Scholar,” Indonesian Journal of Information Systems (IJIS, vol. 2, no. 2, 2020, [Online]. Available: http://garuda.ristekdikti.go.id/,
N. Adila, “Implementation of Web Scraping for Journal Data Collection on the SINTA Website,” Sinkron, vol. 7, no. 4, pp. 2478–2485, Oct. 2022, doi: 10.33395/sinkron.v7i4.11576.
Y. Adilaksa and A. Musdholifah, “Recommendation System for Elective Courses using Content-based Filtering and Weighted Cosine Similarity,” in 2021 4th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2021, Institute of Electrical and Electronics Engineers Inc., 2021, pp. 51–55. doi: 10.1109/ISRITI54043.2021.9702788.
R. Al Rasyid, D. Handayani, and U. Ningsih, “Penerapan Algoritma TF-IDF dan Cosine Similarity untuk Query Pencarian Pada Dataset Destinasi Wisata,” Jurnal Teknologi Informasi dan Komunikasi), vol. 8, no. 1, pp. 171–177, 2024, doi: 10.35870/jti.
E. M. Sipayung, “Sentiment on Public Trust Using the NLP Rule Based Method,” Jurnal Sistem dan Teknologi Informasi (JustIN), vol. 12, no. 1, pp. 175–182, Jan. 2024, doi: 10.26418/justin.v12i1.72426.
L. Hickman, S. Thapa, L. Tay, M. Cao, and P. Srinivasan, “Text Preprocessing for Text Mining in Organizational Research: Review and Recommendations,” Organ Res Methods, vol. 25, no. 1, pp. 114–146, Jan. 2022, doi: 10.1177/1094428120971683.
R. Rismanto, A. R. Syulistyo, and B. P. C. Agusta, “Research supervisor recommendation system based on topic conformity,” International Journal of Modern Education and Computer Science, vol. 12, no. 1, pp. 26–34, 2020, doi: 10.5815/ijmecs.2020.01.04.
C. Jeong, S. Jang, H. Shin, E. Park, and S. Choi, “A Context-Aware Citation Recommendation Model with BERT and Graph Convolutional Networks,” in The Association Of Computational Linguistics Anthology Network, Mar. 2019. [Online]. Available: http://arxiv.org/abs/1903.06464
Z. Fayyaz, M. Ebrahimian, D. Nawara, A. Ibrahim, and R. Kashef, “Recommendation systems: Algorithms, challenges, metrics, and business opportunities,” Applied Sciences (Switzerland), vol. 10, no. 21, pp. 1–20, Nov. 2020, doi: 10.3390/app10217748.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Implementasi LDA, TF-IDF, dan BERT dalam Sistem Rekomendasi Dosen Pembimbing untuk Mahasiswa
Pages: 2175-2183
Copyright (c) 2025 Mutiara Syabilla, Junta Zeniarja, Qotrunnada Nabila
This work is licensed under a Creative Commons Attribution 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 Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment 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 acknowledgment 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 (Refer to The Effect of Open Access).
