ANALISIS ISU SOSIAL MAHASISWA BERBASIS DATA MEDIA SOSIAL MENGGUNAKAN LATENT DIRICHLET ALLOCATION (LDA)
Analysis Of Student Social Issues Based On Social Media Data Using Latent Dirichlet Allocation (LDA)
DOI:
https://doi.org/10.59896/aqlu.v4i1.485Keywords:
LDA, student social issues, social media, linear algebra, text analysisAbstract
This study aims to identify the most frequently discussed social issues among university student on social media platforms such as TikTok and Instagram. Data were collected via a questionnaire distributed to 50 students, with 49 valid responses analyzed. The Latent Dirichlet Allocation (LDA) method based on linear algebra was applied to classify text data into several main topics.
The result revealed three primary clusters of social issues: (1) gender equality and discrimination within the campus environment, (2) educational costs, mental health, and student welfare, and (3) campus politics and career opportunities. Campus politics emerged as the most dominant topic among others. These findings suggest that student actively utilize social media to express their views and respond to institutional policies that directly affect their academic lives. Furthermore, this research demonstrates the effectiveness of the LDA method in analyzing social data to reveal digital communication patterns among student
References
Alpiana, V., Salam, A., Alzami, F., Rizqa, I., & Aqmala, D. (2024). Analisis Topic-Modelling Menggunakan Latent Dirichlet Allocation (LDA) Pada Ulasan Sosial Media Youtube. Jurnal Media Informatika Budidarma, 8(1), 332. https://doi.org/10.30865/mib.v8i1.7127
Andika, M., Chaerani, L., Data, K. K., Allocation, L. D., Online, M., & Topik, P. (2021). Pemodelan Topik Berita pada Portal Berita Online Berbahasa Indonesia Menggunakan Latent Dirichlet Allocation (LDA). 20, 173–180.
Azzura, E. P., Mutahir, A., Hariyadi, H., & Dadan, S. (2025). Penggunaan Bahasa dalam Media Sosial X untuk Mengungkapkan Permasalahan Akademik Mahasiswa (Analisis Wacana Kritis Akun @unsoedmfs). Jurnal Penelitian Inovatif, 5(3), 2205–2224. https://doi.org/10.54082/jupin.566
Farqi, A. F. (2023). Kesetaraan Gender Di Area Kampus Universitas Jember. 3(4).
Jelodar, H., Wang, Y., Yuan, C., & Feng, X. (2017). Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey.
Nafi, K., Sholehah, R., & Rahim, N. (2024). Unveiling Insights : A Knowledge Discovery Approach to Comparing Topic Modeling Techniques in Digital Health Research. 8(1), 108–121.
Nawang Sari, W. A., & Dwi Purnomo, H. (2022). Topic Modeling Using the Latent Dirichlet Allocation Method on Wikipedia Pandemic Covid-19 Data in Indonesia. Jurnal Teknik Informatika (Jutif), 3(5), 1223–1230. https://doi.org/10.20884/1.jutif.2022.3.5.321
Puspita, E., Shiddieq, D. F., & Roji, F. F. (2024). Topic Modeling on Online News Media Using Latent Diriclet Allocation (Case Study Somethinc Brand). MALCOM: Indonesian Journal of Machine Learning and Computer Science, 4(2), 481–489.
Surya Buana, G., Tyasnurita, R., Cahya Puspita, N., Aulia Vinarti, R., & Mahananto, F. (2024). 1636-6477-1-Pb. International Journal on Informatics Visualization, 8(March), 88–95.
Wilkes, J., & Riswani, R. (2022). Mental Wellbeing of Indonesian Students : Mean Comparison with UK Students and Relationships with Self-Compassion and Academic Engagement.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Jesisca Jesisca, Chodri Dwi Yonny
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
