Implementasi Content-Based Filtering dan Singular Value Decomposition untuk Rekomendasi Film

Muhammad Iqbal Pradipta; Mhd. Basri

doi:10.70340/jirsi.v5i3.682

Penulis

Muhammad Iqbal Pradipta Universitas Muhammadiyah Sumatera Utara
Mhd. Basri Universitas Muhammadiyah Sumatera Utara

DOI:

https://doi.org/10.70340/jirsi.v5i3.682

Kata Kunci:

TF-IDF, cosine similarity, content-based filtering, SVD, movie recommendation

Abstrak

Pertumbuhan katalog layanan video daring menimbulkan kelebihan informasi yang menyulitkan pengguna menemukan film sesuai preferensi. Penelitian ini bertujuan membangun dan mengevaluasi dua pendekatan sistem rekomendasi film, yaitu content-based filtering menggunakan TF-IDF dan cosine similarity serta collaborative filtering menggunakan Singular Value Decomposition (SVD). Data penelitian mencakup 4.803 film beserta kredit produksi dan 100.004 interaksi rating pengguna. Tahapan penelitian meliputi pembersihan dan integrasi data, pembentukan representasi konten, pemodelan faktor laten, pembagian data latih dan uji sebesar 75:25, serta evaluasi menggunakan Precision dan Root Mean Squared Error. Hasil pengujian menunjukkan bahwa rekomendasi berbasis konten memperoleh Precision 0,70 berdasarkan kesesuaian genre, sedangkan rekomendasi berbasis sutradara dan aktor mencapai presisi 1,00 karena fitur pemeringkatan identik dengan kriteria relevansi. Model SVD menghasilkan RMSE 0,9007 dan mampu memberikan rekomendasi personal berdasarkan pola rating pengguna. Kontribusi penelitian terletak pada evaluasi dua baseline dengan tujuan berbeda, analisis potensi bias pada pengukuran presisi, serta penegasan pentingnya konsistensi identitas film lintas dataset. Content-based filtering efektif untuk menemukan film serupa berdasarkan metadata, sedangkan SVD mampu memodelkan preferensi laten pengguna, tetapi hasil kedua pendekatan harus ditafsirkan menggunakan metrik yang sesuai.

Unduhan

Data unduhan belum tersedia.

Referensi

S. Airen and J. Agrawal, “Movie Recommender System Using Parameter Tuning of User and Movie Neighbourhood via Co-Clustering,” Procedia Computer Science, vol. 218, pp. 1176-1183, 2023, doi: 10.1016/j.procs.2023.01.096.

G. Behera and N. Nain, “Collaborative Filtering with Temporal Features for Movie Recommendation System,” Procedia Computer Science, vol. 218, pp. 1366-1373, 2023, doi: 10.1016/j.procs.2023.01.115.

F. Horasan, A. H. Yurttakal, and S. Gündüz, “A novel model based collaborative filtering recommender system via truncated ULV decomposition,” Journal of King Saud University - Computer and Information Sciences, vol. 35, no. 8, art. 101724, 2023, doi: 10.1016/j.jksuci.2023.101724.

M. M. Bendouch, F. Frasincar, and T. Robal, “A visual-semantic approach for building content-based recommender systems,” Information Systems, vol. 117, art. 102243, 2023, doi: 10.1016/j.is.2023.102243.

H. H. Kurniawan, W. S. Lukman, R. Fredyan, and M. A. Ibrahim, “Movie Recommendation System: A Comparison of Content-Based and Collaborative Filtering,” Procedia Computer Science, vol. 245, pp. 860-868, 2024, doi: 10.1016/j.procs.2024.10.313.

R. Nesmaoui, M. Louhichi, and M. Lazaar, “A Collaborative Filtering Movies Recommendation System based on Graph Neural Network,” Procedia Computer Science, vol. 220, pp. 456-461, 2023, doi: 10.1016/j.procs.2023.03.058.

Y. Tao, F. Kong, Y. Shi, J. Yu, and X. Wang, “Efficient, secure and verifiable outsourcing scheme for SVD-based collaborative filtering recommender system,” Future Generation Computer Systems, vol. 149, pp. 445-454, 2023, doi: 10.1016/j.future.2023.07.042.

Y. Yang, K. Woradit, and K. Cosh, “Hybrid Movie Recommendation System With User Partitioning and Log Likelihood Content Comparison,” IEEE Access, vol. 13, pp. 11609-11622, 2025, doi: 10.1109/ACCESS.2025.3529515.

A. M. Sarhan, H. Ayman, M. Wagdi, B. Ali, A. Adel, and R. Osama, “Integrating machine learning and sentiment analysis in movie recommendation systems,” Journal of Electrical Systems and Information Technology, vol. 11, art. 53, 2024, doi: 10.1186/s43067-024-00177-7.

F. Fkih, “Similarity measures for Collaborative Filtering-based Recommender Systems: Review and experimental comparison,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 9, pp. 7645-7669, 2022, doi: 10.1016/j.jksuci.2021.09.014.

D. Roy and M. Dutta, “A systematic review and research perspective on recommender systems,” Journal of Big Data, vol. 9, art. 59, 2022, doi: 10.1186/s40537-022-00592-5.

F. M. Harper and J. A. Konstan, “The MovieLens Datasets: History and Context,” ACM Transactions on Interactive Intelligent Systems, vol. 5, no. 4, art. 19, 2015, doi: 10.1145/2827872.

M. I. Pradipta, “Movie Dataset,” Hugging Face Datasets, 2024. [Online]. Available: https://huggingface.co/datasets/mhdiqbalpradipta/movie. [Accessed: Jul. 24, 2026].