cover
Contact Name
Erwin Mardinata Utama
Contact Email
alpha.publine@gmail.com
Phone
+6281882840231
Journal Mail Official
alpha.publine@gmail.com
Editorial Address
Jl. Kompleks Perumahan Karang Sukun, Mataram Timur - NTB 83121
Location
Kota mataram,
Nusa tenggara barat
INDONESIA
Journal of Science and Technology: Alpha
ISSN : -     EISSN : 30894298     DOI : https://doi.org/10.70716/alpha
ALPHA: Journal of Science and Technology is a peer-review journal that could be access to the public, published by Lembaga Publikasi Ilmiah Nusantara with registered number ISSN 3089-4298. ALPHA provides a platform for researchers, academics, professionals, practitioners and students to embed and share knowledge in the form of empirical and theoretical research papers, case studies, literature reviews and book reviews related to science and technology research. ALPHA welcomes and recognizes high quality theoretical and empirical research papers, case studies, review papers, literature reviews, book reviews, conceptual frameworks, analysis and simulation models, technical notes related to research from researchers, academics, professionals, practitioners, and students.
Arjuna Subject : Umum - Umum
Articles 21 Documents
Klasifikasi Ulasan Mahasiswa tentang Fasilitas dan Pelayanan Perguruan Tinggi Swasta PGRI dengan BiLSTM Nururrahman, Nazdaen Akbar
Journal of Science and Technology: Alpha Vol. 2 No. 1 (2026): Journal of Science and Technology: Alpha, January 2026
Publisher : Lembaga Publikasi Ilmiah Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70716/alpha.v2i1.358

Abstract

Student satisfaction with campus facilities and services is an important indicator in assessing the quality of higher education. This study develops a system for classifying student reviews related to facilities and services at PGRI Private Universities using the Bidirectional Long Short-Term Memory (BiLSTM) method. The research data consist of 3,067 student reviews collected through Google Forms and Google Maps, covering five service aspects: Physical Facilities and Core Infrastructure; Academic Support Facilities and Learning Resources; Administrative Services and Staff; Facilities and Environment Supporting Non-Academic Activities; and Security and Accessibility. The BiLSTM method with 300-dimensional FastText word embeddings is employed to classify reviews into service aspect categories and satisfaction levels (Very Satisfied, Satisfied, Moderately Satisfied, Less Satisfied, and Not Satisfied). The model architecture comprises two BiLSTM layers with 128 and 64 units, respectively, along with a dropout mechanism to reduce the risk of overfitting. Model performance is evaluated using a confusion matrix, precision, recall, F1-score, and overall accuracy. The results indicate that the BiLSTM model is able to classify service aspects with good accuracy, although the performance of satisfaction level classification is still affected by data imbalance and the similarity of expressions across satisfaction categories. Overall, the proposed system can provide automated analysis of student reviews and serve as a decision-support tool for universities in understanding service quality based on review data in a more objective and structured manner.

Page 3 of 3 | Total Record : 21