SISTEM REKOMENDASI MUSIK MENGGUNAKAN METODE HYBRID COLLABORATIVE FILTERING DAN CONTENT-BASED FILTERING

    Ariel Jusuf Indrastata, - and Yudi Wibisono, - and Muhamad Nursalman, - (2025) SISTEM REKOMENDASI MUSIK MENGGUNAKAN METODE HYBRID COLLABORATIVE FILTERING DAN CONTENT-BASED FILTERING. S1 thesis, Universitas Pendidikan Indonesia.

    Abstract

    Musik adalah sarana hiburan yang dikonsumsi oleh berbagai kalangan masyarakat. Selain sebagai hiburan, musik juga menjadi media ekspresi diri dan sarana komunikasi. Kemajuan teknologi memudahkan masyarakat untuk mengkonsumsi musik secara digital. Namun, dengan banyaknya pilihan lagu dalam katalog digital, pendengar musik akan kewalahan untuk mendapatkan lagu yang sesuai dengan seleranya. Untuk mengatasi hal tersebut, penelitian ini akan membangun sistem rekomendasi musik menggunakan metode hybrid collaborative filtering dan content-based filtering. Data yang digunakan dalam penelitian ini adalah riwayat pemutaran lagu oleh pendengar musik dan fitur audio yang merepresentasikan karakteristik dari lagu. Walaupun hasil pengujian sistem rekomendasi musik dengan metode hybrid menunjukkan nilai F1-Score yang rendah, yaitu sebesar 6,8%, namun sistem rekomendasi mampu memberikan setidaknya satu lagu rekomendasi yang relevan kepada 71,37% pengguna. Music is a form of entertainment consumed by various groups of people. In addition to being an entertainment, music also serves as a medium of self expression and communication. Technological advances have made it easier for people to consume music digitally. However, with the large selection of songs in digital catalogs, music listeners may find it overwhelming to find songs that suit their tastes. To address this issue, this study will develop a music recommendation system using a hybrid collaborative filtering and content-based filtering method. The data used in this study are the music listener's song playback history and audio features that represent the characteristics of the song. Although the results of testing the music recommendation system using the hybrid method showed a low F1-Score of 6.8%, the recommendation system was able to provide at least one relevant song recommendation to 71.37% of users.

    Baca Full Text klik disini
    [thumbnail of S_KOM_1805152_Title.pdf] Text
    S_KOM_1805152_Title.pdf
    Download (1MB)
    [thumbnail of S_KOM_1805152_Chapter1.pdf] Text
    S_KOM_1805152_Chapter1.pdf
    Download (677kB)
    [thumbnail of S_KOM_1805152_Chapter2.pdf] Text
    S_KOM_1805152_Chapter2.pdf
    Restricted to Staf Perpustakaan
    Download (1MB)
    [thumbnail of S_KOM_1805152_Chapter3.pdf] Text
    S_KOM_1805152_Chapter3.pdf
    Download (904kB)
    [thumbnail of S_KOM_1805152_Chapter4.pdf] Text
    S_KOM_1805152_Chapter4.pdf
    Restricted to Staf Perpustakaan
    Download (2MB)
    [thumbnail of S_KOM_1805152_Chapter5.pdf] Text
    S_KOM_1805152_Chapter5.pdf
    Download (668kB)
    Official URL: https://repository.upi.edu/
    Item Type: Thesis (S1)
    Additional Information: https://scholar.google.com/citations?user=mLRwHIwAAAAJ&hl=en ID SINTA Dosen Pembimbing: Yudi Wibisono: 260167 Muhamad Nursalman: 6143456
    Uncontrolled Keywords: Sistem Rekomendasi Musik, Collaborative Filtering, Content-Based Filtering, Hybrid Filtering. Music Recommendation System, Collaborative Filtering, Content-Based Filtering, Hybrid Filtering.
    Subjects: L Education > L Education (General)
    Q Science > QA Mathematics > QA75 Electronic computers. Computer science
    Divisions: Fakultas Pendidikan Matematika dan Ilmu Pengetahuan Alam > Program Studi Ilmu Komputer
    Depositing User: Ariel Jusuf Indrastata
    Date Deposited: 09 Sep 2025 09:41
    Last Modified: 09 Sep 2025 09:41
    URI: http://repository.upi.edu/id/eprint/138341

    Actions (login required)

    View Item View Item