Analisis Tren Topik Berbasis BERTopic untuk Pendukung Keputusan Akademik Teknik Sipil: BERTopic-Based Analysis of Student Research Trends for Academic Decision Support

Ayang Yugo Pratomo; Naeli Umniati

doi:10.57152/malcom.v6i4.3035

Authors

Ayang Yugo Pratomo Universitas Gunadarma
Naeli Umniati Universitas Gunadarma

DOI:

https://doi.org/10.57152/malcom.v6i4.3035

Keywords:

Analisis Tren Penelitian, BERTopic, Latent Dirichlet Allocation, Sentence-BERT

Abstract

Penelitian ini menganalisis tren topik tugas akhir mahasiswa Teknik Sipil Universitas Mercu Buana periode 2021–2025 dan merumuskan rekomendasi akademik berbasis data. Kerangka CRISP-DM diterapkan pada 1.532 dokumen yang memuat atribut tahun, judul, dan abstrak. Teks dipraproses, direpresentasikan menggunakan Sentence-BERT, dan dimodelkan dengan BERTopic, sedangkan Latent Dirichlet Allocation (LDA) digunakan sebagai pembanding pada korpus dan jumlah topik yang sama. Analisis sensitivitas menguji sembilan kombinasi parameter UMAP–HDBSCAN. Konfigurasi terpilih menghasilkan 22 topik dengan Topic Coherence 0,7807, Topic Diversity 0,7909, dan 253 dokumen outlier, sedangkan LDA memperoleh nilai masing-masing 0,6334 dan 0,8273. Kebaruan penelitian terletak pada integrasi evaluasi komparatif pemodelan topik, analisis tren yang diperkuat secara statistik, pemetaan semantik otomatis ke bidang konsentrasi yang dilanjutkan dengan pemetaan institusional PEO, serta rekomendasi berbasis aturan yang transparan. Arah tren ditentukan menggunakan slope, sedangkan p-value dan R-squared digunakan untuk mendukung interpretasi kekuatan statistik. Building Information Modeling dan penjadwalan CPM/PERT meningkat secara signifikan, sedangkan Earned Value Management serta hidrologi dan drainase menurun secara signifikan. Hasil analisis diintegrasikan ke dalam Sistem Pendukung Keputusan Akademik hibrida semantik-statistik yang menggabungkan pemetaan berbasis Sentence-BERT dan aturan keputusan untuk menghasilkan rekomendasi awal berupa pengembangan, pemeliharaan, pemantauan, evaluasi, dan revitalisasi bidang penelitian

Downloads

Download data is not yet available.

References

A. Subakti, H. Murfi, and N. Hariadi, “The performance of BERT as data representation of text clustering,” J. Big Data, vol. 9, no. 1, 2022, doi: 10.1186/s40537-022-00564-9.

R. Egger and J. Yu, “A Topic Modeling Comparison Between LDA, NMF, Top2Vec, and BERTopic to Demystify Twitter Posts,” Front. Sociol., vol. 7, no. May, pp. 1–16, 2022, doi: 10.3389/fsoc.2022.886498.

Nursyahrina, S. Defit, and R. Sovia, “Metode BERTopic dan LDA untuk Analisis Tren Penelitian Bidang Ilmu Komputer,” J. KomtekInfo, vol. 11, no. 4, pp. 332–341, 2024, doi: 10.35134/komtekinfo.v11i4.580.

Q. Lin et al., “Research on Topic Mining and Evolution Trends of Functional Agriculture Based on the BERTopic Model,” Agric., vol. 14, no. 10, 2024, doi: 10.3390/agriculture14101691.

K.-K. Lai, C.-W. Hsiao, and Y.-J. Hsu, “Strategic Management Knowledge Map via BERTopic (1980–2025): Evolution, Integration, and Application,” Appl. Syst. Innov., vol. 8, no. 5, p. 142, Sep. 2025, doi: 10.3390/asi8050142.

N. Novarian, S. Khomsah, and A. B. Arifa, “Topic Modeling Tugas Akhir Mahasiswa Fakultas Informatika Institut Teknologi Telkom Purwokerto Menggunakan Metode Latent Dirichlet Allocation,” LEDGER J. Inform. Inf. Technol., vol. 2, no. 1, pp. 14–27, 2023.

T. Titiana and D. H. Bangkalang, “Analisis Dan Penerapan Topic Modeling Pada Judul Tugas Akhir Mahasiswa Menggunakan Metode Latent Dirichlet Allocation (Lda),” JIPI (Jurnal Ilm. Penelit. dan Pembelajaran Inform., vol. 8, no. 4, pp. 1275–1287, 2023, doi: 10.29100/jipi.v8i4.4254.

S. Maniyan, R. Ghousi, and A. Haeri, “Data mining-based decision support system for educational decision makers: Extracting rules to enhance academic efficiency,” Comput. Educ. Artif. Intell., vol. 6, no. July 2023, p. 100242, Jun. 2024, doi: 10.1016/j.caeai.2024.100242.

M. Grootendorst, “BERTopic: Neural topic modeling with a class-based TF-IDF procedure,” 2022, [Online]. Available: http://arxiv.org/abs/2203.05794

L. R. Nisa, A. Luthfiarta, A. Nugraha, M. M. Hasan, A. Wulandari, Kang, and A. M. Huda, “A TOPIC-BASED APPROACH FOR RECOMMENDING UNDERGRADUATE THESIS SUPERVISOR USING LDA WITH COSINE SIMILARITY,” J. Tek. Inform., vol. 6, no. 1, pp. 311–323, Feb. 2025, doi: 10.52436/1.jutif.2025.6.1.4061.

Y. An, H. Oh, and J. Lee, “Marketing Insights from Reviews Using Topic Modeling with BERTopic and Deep Clustering Network,” Appl. Sci., vol. 13, no. 16, 2023, doi: 10.3390/app13169443.

P. C. Bhatt, Y. C. Hsu, K. K. Lai, and V. A. Drave, “Technology Convergence Assessment by an Integrated Approach of BERT Topic Modeling and Association Rule Mining,” IEEE Trans. Eng. Manag., vol. 72, pp. 1699–1713, 2025, doi: 10.1109/TEM.2025.3556006.

S. Anggai, R. M. Zain, T. Tukiyat, and A. A. Waskita, “Enhancing BERTopic with Neural Network Clustering for Thematic Analysis of U.S. Presidential Speeches,” J. Tek. Inform., vol. 6, no. 4, pp. 1957–1970, Aug. 2025, doi: 10.52436/1.jutif.2025.6.4.5090.

H. Hairani, M. Janhasmadja, A. Tholib, J. Ximenes Guterres, and Y. Ariyanto, “Thesis Topic Modeling Study: Latent Dirichlet Allocation (LDA) and Machine Learning Approach,” Int. J. Eng. Comput. Sci. Appl., vol. 3, no. 2, pp. 51–60, 2024, doi: 10.30812/ijecsa.v3i2.4375.

O. S. Nufi and Khalid, “Topic Modelling Skripsi Manajemen Dakwah PTKIN menggunakan Latent Dirichlet Allocation (LDA),” Remik Ris. dan E-Jurnal Manaj. Inform. Komput., vol. 9, no. 2, pp. 539–549, 2025, [Online]. Available: https://www.jurnal.polgan.ac.id/index.php/remik/article/view/14671

W. Janssens, M. Bogaert, and D. Van Den Poel, “A Comparative Analysis of Topic Reduction Techniques for BERTopic,” IEEE Access, vol. 13, no. December, pp. 204087–204103, 2025, doi: 10.1109/ACCESS.2025.3638956.

Y. Liu and F. Wan, “Unveiling temporal and spatial research trends in precision agriculture: A BERTopic text mining approach,” Heliyon, vol. 10, no. 17, p. e36808, 2024, doi: 10.1016/j.heliyon.2024.e36808.

A. Bachoumis, C. Mylonas, K. Plakas, M. Birbas, and A. Birbas, “Data-Driven Analytics for Reliability in the Buildings-to-Grid Integrated System Framework: A Systematic Text-Mining-Assisted Literature Review and Trend Analysis,” IEEE Access, vol. 11, no. October, pp. 130763–130787, 2023, doi: 10.1109/ACCESS.2023.3335191.

S. Umamaheswaran, V. Dar, E. Sharma, and J. S. Kurian, “Mapping Climate Themes from 2008-2021 - An Analysis of Business News Using Topic Models,” IEEE Access, vol. 11, no. March, pp. 26554–26565, 2023, doi: 10.1109/ACCESS.2023.3256530.

N. Kardam and D. Wilson, “A comparative analysis of topic modelling techniques for the thematic analysis of student feedback,” PLoS One, vol. 21, no. 8, pp. 1–32, 2026, doi: 10.1371/journal.pone.0328697.