Analisis Sentimen Mahasiswa terhadap Kualitas Jaringan Internet UINSU Tuntungan Menggunakan Algoritma SVM

Abstract

The unstable internet network quality at UINSU Campus IV Tuntungan has become one of the obstacles in supporting students’ academic activities, particularly in digital learning processes, accessing references, and uploading assignments. This study aims to analyze students’ sentiment toward the campus internet network quality using the Support Vector Machine (SVM) algorithm. Data were collected through interviews and Google Forms, then processed through several stages: preprocessing, sentiment labeling using a lexicon-based method, feature weighting with TF-IDF, and classification using SVM. The results show that most students expressed negative sentiment, particularly regarding perceptions of slow and unstable network performance. The SVM model used in this study was able to classify sentiments with an accuracy of 88.78%, supported by balanced precision, recall, and F1-score values. These findings indicate that SVM is effective in identifying student opinions and can serve as a basis for the campus to evaluate and improve the quality of its internet network services.