The Academic Information System (SIMAK) at Sriwijaya University plays a crucial role in facilitating student academic activities; however, it faces several technical issues that affect user satisfaction, including server outages and challenges in data access. This dissatisfaction serves as a vital metric for evaluating the system's effectiveness. This study aims to analyze student sentiment regarding SIMAK utilizing the Naïve Bayes method. A total of 92 tweets were gathered from Twitter through web scraping, which were then categorized into manually labeled training and test datasets for model validation. The data underwent processing that included text cleaning and the application of Term Frequency-Inverse Document Frequency (TF-IDF) to assess the significance of words within a collection of documents. The evaluation results indicated that the model achieved an accuracy of 65%, with a precision of 63% for negative sentiment and a recall of 100%. In contrast, positive sentiment exhibited a low precision of 12.5% and an F1-score of 22.2%, highlighting difficulties in identifying positive sentiment due to data imbalance. The model demonstrated greater effectiveness in identifying user grievances, particularly concerning server disruptions, data delays, and challenges in completing Study Plan Cards and accessing grades. These findings provide valuable insights for SIMAK maintainers to enhance system reliability and user experience. Future research should aim to broaden data coverage and explore alternative analytical methods to yield more representative outcomes.