Perancangan Sistem Rekomendasi Band pada Festival Musik Menggunakan Metode Content-Based Filtering
DOI:
https://doi.org/10.47701/0c4ww052Keywords:
Content-based filtering, cosine similarity, festival musik, sistem rekomendasi, TF-IDFAbstract
Sistem rekomendasi memiliki peran penting dalam membantu pengambilan keputusan, termasuk dalam konteks penyelenggaraan festival musik. Penelitian ini bertujuan untuk merancang dan mengimplementasikan sistem rekomendasi band pada festival musik menggunakan metode Content-Based Filtering (CBF). Dataset terdiri dari 15 band lokal dan nasional dengan profil konten berupa genre, mood lagu, asal daerah, gaya lirik, dan pengaruh musikal. Data diolah menggunakan TF- IDF untuk menghasilkan representasi vektor, dan kemiripan dihitung dengan cosine similarity. Hasil pengujian menunjukkan bahwa sistem berhasil merekomendasikan 5 band teratas dengan skor kemiripan tertinggi, misalnya THE JEBLOGS (0,391), REBELLION ROSE (0,265), dan LOS JANTOS (0,230) ketika pengguna memilih SUPERMAN IS DEAD sebagai input. Hasil ini menunjukkan sistem mampu menangkap kesamaan tematik secara efektif. Sistem ini dapat digunakan sebagai alat bantu dalam proses kurasi line-up festival yang lebih konsisten dan terarah. Ke depan, sistem dapat dikembangkan dengan mengintegrasikan preferensi pengguna atau pendekatan hybrid.
References
[1] S. Mukhopadhyay, A. Kumar, D. Parashar, and M. Singh, “Enhanced Music Recommendation Systems: A Comparative Study of Content-Based Filtering and K-Means Clustering Approaches,” Rev. Intell. Artif., vol. 38, no. 1, pp. 365–376, Feb. 2024, doi: 10.18280/ria.380138.
[2] R. Salganik, F. Diaz, and G. Farnadi, “Fairness Through Domain Awareness: Mitigating Popularity Bias For Music Discovery,” 2023, arXiv. doi: 10.48550/ARXIV.2308.14601.
[3] F. Christyawan, A. N. Rohman, and A. D. Hartanto, “Application of Content-Based Filtering Method Using Cosine Similarity in Restaurant Selection Recommendation System,” J. Inf. Syst. Inform., vol. 6, no. 3, pp. 1559–1576, Sep. 2024, doi: 10.51519/journalisi.v6i3.806.
[4] “Asymmetrically Weighted Cosine Similarity Measure for Recommendation Systems,” in Lecture Notes in Networks and Systems, Singapore: Springer Nature Singapore, 2022, pp. 489–500. doi: 10.1007/978-981-19-1018-0_42.
[5] G. Yunanda, D. Nurjanah, and S. Meliana, “Recommendation System from Microsoft News Data using TF-IDF and Cosine Similarity Methods,” Build. Inform. Technol. Sci. BITS, vol. 4, no. 1, Jun. 2022, doi: 10.47065/bits.v4i1.1670.
[6] A. Kurniaji and R. C. N. Santi, “Implementasi Metode Content Based Filtering Pada Pemilihan Komik,” J. Inform., vol. 10, no. 2, pp. 109–117, Oct. 2023, doi: 10.31294/inf.v10i2.16113.
[7] F. Meggetto, C. Revie, J. Levine, and Y. Moshfeghi, “Why People Skip Music? On Predicting Music Skips using Deep Reinforcement Learning,” 2023, doi: 10.48550/ARXIV.2301.03881.
[8] Z. Bingyu and N. Arefyev, “The Document Vectors Using Cosine Similarity Revisited,” in Proceedings of the Third Workshop on Insights from Negative Results in NLP, Dublin, Ireland: Association for Computational Linguistics, 2022, pp. 129–133. doi: 10.18653/v1/2022.insights-1.17.
[9] Y. Shi and Y. Chung, “Learning Similarity Preserving Binary Codes for Recommender Systems,” 2022, arXiv. doi: 10.48550/ARXIV.2204.08569.
[10] Y. Deldjoo, M. Schedl, and P. Knees, “Content-driven music recommendation: Evolution, state of the art, and challenges,” Comput. Sci. Rev., vol. 51, p. 100618, Feb. 2024, doi: 10.1016/j.cosrev.2024.100618.
[11] M. Gao, Y. Luo, and X. Hu, “Online Course Recommendation Using Deep Convolutional Neural Network with Negative Sequence Mining,” Wirel. Commun. Mob. Comput., vol. 2022, pp. 1–7, Aug. 2022, doi: 10.1155/2022/9054149.
