Analyzing Social Media Sentiment on Telkom University National Campus: Insights into Public Opinion

In the digital era, social media has become a primary platform for the public to express opinions, including educational institutions like Telkom University (Tel-U). Understanding public sentiment toward Tel-U is crucial for institutional decision-making, as it helps shape strategies for improvement and address concerns. This study compares the performance of Support Vector Machine (SVM) and Random Forest (RF) algorithms in classifying public sentiment toward Tel-U branch campuses. The dataset consists of 2,600 social media comments collected from 2022 to 2025, categorized into positive, negative, and neutral sentiments. NLP preprocessing steps, including tokenization, stopword removal, and stemming, were applied to clean the data, followed by feature extraction using the Term Frequency-Inverse Document Frequency (TF-IDF) method before training the models. The results show that SVM outperforms RF, achieving an accuracy of 0.73 compared to 0.70. This study is the first to analyze public sentiment toward Tel-U branch campuses using a newly collected dataset, offering up-to-date insights into public perceptions. The findings suggest that machine learning models can serve as reliable tools for dynamically understanding public opinion. The results of this study can help Tel-U make more informed strategic decisions, improve academic policies, enhance student satisfaction, and respond more effectively to public concerns.