Skripsi
SISTEM REKOMENDASI MUSIK MENGGUNAKAN METODE CONTENT-BASED FILTERING DAN ALGORITMA TERM FREQUENCY-INVERSE DOCUMENT FREQUENCY (TF-IDF).
The development of music streaming platforms has created a "paradox of choice" phenomenon, where the abundance of music options makes it difficult for users to find songs that match their preferences. This research develops a music recommendation system using Content-Based Filtering method and Term Frequency-Inverse Document Frequency (TF-IDF) algorithm to address this issue. The study aims to design a system capable of analyzing song characteristics and providing personalized music recommendations. Content-Based Filtering is used to identify song feature similarities, while TF-IDF helps extract and weight representative features. Cosine similarity is utilized to measure the similarity between songs. The system was tested using a music dataset with variations in size from 5,000 to 25,000 songs. Test results show excellent performance, with high precision, recall, and F1 scores, especially at thresholds of 0.3-0.4. Resulting average value for precision of 0.90, recall 0.77, and f1 score 0.80. The research proves that this approach effectively provides accurate recommendations across genres and artists. The study concludes that Content-Based Filtering and TF-IDF were successfully implemented in the music recommendation system, with significant potential to enhance user experience on music streaming platforms.
| Title | Edition | Language |
|---|---|---|
| OPTIMASI SISTEM REKOMENDASI BUKU DENGAN METODE CONTENT-BASED FILTERING | - | id |