Topik Modelling Skripsi Prodi Teknik Lingkungan di Jawa Timur Menggunakan Metode LDA
Abstract
In higher education, the undergraduate thesis represents a tangible contribution of students to the development of scientific knowledge. In the field of Environmental Engineering, student research often focuses on issues that are closely related to both local and global environmental challenges. This study aims to analyze the main themes of undergraduate theses written by Environmental Engineering students in East Java using the Latent Dirichlet Allocation (LDA) method. The research data were collected from thesis titles and abstracts obtained from several universities. Through the application of LDA, several dominant themes were identified, including waste management, water quality, air pollution reduction, and the application of environmental treatment technologies. The results indicate that LDA is capable of uncovering research patterns and clustering topics that reflect the primary concerns of students in this field. These findings not only provide insights into the current research trends among students but also serve as a reference for curriculum development, research planning, and academic decision-making. Thus, this study contributes to improving the quality of education while mapping future research directions in Environmental Engineering.
Downloads
References
Universitas Pembangunan Nasional Veteran Jawa Timur, Analisis dampak pencemaran lingkungan pada IPAL PT. SIER Surabaya dengan metode life cycle assessment (LCA), Skripsi, Prodi Teknik Lingkungan, 2021.
Universitas Islam Negeri Sunan Ampel Surabaya, Analisis jejak karbon (carbon footprint) pada aktivitas permukiman dan kualitas air di Jawa Timur, Skripsi, Prodi Teknik Lingkungan, 2022.
Universitas Pembangunan Nasional Veteran Jawa Timur, Potensi produksi gas metana dari landfilling di TPA Bengkala Kabupaten Buleleng dengan kombinasi model LandGEM, IPCC, dan LCA, Skripsi, Prodi Teknik Lingkungan, 2023.
G. Supiadin and A. D. Laksito, “Evaluating LDA and LSA for topic modeling in the Indonesian natural disaster,” Int. J. Comput. Sci. (IJCS), 2023.
H. Hairani, M. Janhasmadja, A. Tholib, J. X. Guterres, and Y. Ariyanto, “Thesis topic modeling study: Latent Dirichlet allocation (LDA) and machine learning approach,” Int. J. Eng. Comput. Sci. Appl. (IJECSA), Universitas Bumigora, 2024.
N. Idrus, Analisis topic modeling menggunakan LDA dan HDP dengan word embedding dan clustering, Tesis, Universitas Gadjah Mada, 2024.
A. Siino, S. Brasini, dan D. Aiello, “Natural Language Processing in the Age of Large Language Models: A Survey on Pre-processing Techniques and Challenges,” Information Processing & Management, vol. 61, no. 6, p. 103678, 2024.
R. A. Berutu, R. Mayasari, dan D. S. Purnamasari, “Text Pre-processing for Indonesian Language in Sentiment Analysis,” Jurnal Infotel, vol. 15, no. 3, pp. 161–170, 2023.
Y. Farea, H. A. Aboalsamh, dan M. A. Bamahdi, “An Enhanced Topic Modeling Approach Using LDA with Optimal Hyperparameters,” Engineering Applications of Artificial Intelligence, vol. 132, p. 107289, 2024.
Casualty Actuarial Society, “Latent Dirichlet Allocation Topic Modeling in Python,” CAS Research Paper, 2023. [Online]. Available: https://www.casact.org/sites/default/files/2023-04/iCAS-4_Latent_Dirichlet_Allocation_Topic_Modeling_in_Python.pdf
D. M. Blei, A. Y. Ng, dan M. I. Jordan, “Latent Dirichlet Allocation Revisited with Modern Applications,” ACM Computing Surveys, vol. 55, no. 12, pp. 1–40, 2022.
H. U. Onah, C. J. C. Burges, dan R. S. W. Onah, “Interactive Topic Visualization for Large-Scale Text Data,” arXiv preprint, arXiv:2207.14687, 2022.
N. Novarian et al., “Topic Modeling Tugas Akhir Mahasiswa Fakultas Informatika,” Ledger, vol. 2, no. 1, Feb. 2023.
A. Farea et al., “Investigating the optimal number of topics by advanced text segmentation for coherence optimization,” Elsevier, 2024.
H. U. Onah et al., “Interactive Topic Visualization for Large-Scale Text Data,” arXiv preprint, 2022.
N. Novarian et al., “Topic Modeling Tugas Akhir Mahasiswa Fakultas Informatika,” Ledger, vol. 2, no. 1, Feb. 2023.
A. Farea et al., “Investigating the optimal number of topics by advanced text segmentation for coherence optimization,” Elsevier, 2024.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under an Attribution 4.0 International (CC BY 4.0) that allows others to share — copy and redistribute the material in any medium or format and adapt — remix, transform, and build upon the material for any purpose, even commercially with an acknowledgment of the work's authorship and initial publication in this journal.
