Answers are grounded in this paper and cite their sources.
This research develops a system for matching thesis supervisors and students based on content-based filtering techniques.
This Final Project is entitled "A Recommendation System for Selecting Thesis Supervisors Based on Content-Based Filtering in the Information Systems Study Program at Bina Darma University." This research aims to develop a recommendation system to assist students in selecting thesis supervisors based on the alignment between the student's proposed thesis topic and the lecturer's expertise. The method used is Content-Based Filtering with the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm for weighting keywords and Cosine Similarity to calculate the similarity level between the student's thesis title and the lecturer's journal publications. The system is built as a web-based application using PHP and MySQL. Testing results based on 30 data samples show that the system provides accurate recommendations with a Precision of 86.7%, a Recall of 80.0%, and an F1-Score of 83.2%. The highest recommendation score achieved was 98.69 for a lecturer whose journal closely matched the proposed thesis title. The implementation of this system is expected to streamline the thesis supervisor selection process, ensuring a more objective and appropriate match between students and supervisors based on their research fields.
No takes yet. Share an insight, caveat, or question.
Oktapiana et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: