<![CDATA[Internship is an academic activity that connects students with real-world work environments, making comments and scores from companies critical data sources for evaluating student achievement and curriculum alignment. In the Information System Study Program at Darma Persada University, company feedback from the 2016-2025 period had not been integrated or analyzed comprehensively, particularly regarding textual comments from corporate HR. This study aims to design, build, and evaluate a internship evaluation information system that processes numerical scores, letter grades, and company textual comments using sentiment analysis. The system was developed using the Rapid Application Development (RAD) methodology through requirements planning, design workshops, rapid construction, and evaluative implementation. Sentiment analysis was implemented via the Hugging Face API service to classify comments into positive, neutral, and negative categories along with their confidence scores. System evaluation was conducted using Black-box testing for functional validity, sentiment classification performance metrics (Accuracy, Precision, Recall, F1-Score), and user assessment using the System Usability Scale (SUS) questionnaire. The test results showed a 100% success rate in Black-box functional testing. The sentiment analysis model achieved an accuracy of 85.0%, precision of 84.6%, recall of 85.0%, and an F1-Score of 84.8% on the sample evaluation set. Furthermore, the system usability assessment via the SUS questionnaire yielded an average score of 82.5, placing the system in the 'Excellent' usability category (Grade A). This system effectively assists the study program in interpreting internship quality patterns objectively, systematically, and in a data-driven manner.]]>
Copyrights © 2026
