Integrating Word Embeddings and IMDb Web Scraping for Keyword-Based Movie Recommendation

Andani Chacha Cahya Dewi; Deni Arifianto; Nanda Kurnia Wardati

doi:10.55537/cosie.v5i3.1839

Authors

Andani Chacha Cahya Dewi Universitas Muhammadiyah Jember
Deni Arifianto Universitas Muhammadiyah Jember
Nanda Kurnia Wardati Universitas Muhammadiyah Jember

DOI:

https://doi.org/10.55537/cosie.v5i3.1839

Keywords:

Sistem Rekomendasi, Content-Based Filtering, Word Embeddings, Word2Vec, Cosine Similarity

Abstract

The rapid growth of the film industry and streaming platforms has led to information overload and filter bubbles that make it difficult for users to find content matching their narrative preferences. Prior content-based filtering approaches relying on word-frequency methods (TFIDF) suffer from a semantic gap and commonly depend on a single public dataset and a reference title (seed movie) as input. This study combines a public dataset with IMDb web-scraping results (a maximum population of 5,000 titles) and applies a Skip-gram Word2Vec model to represent movie synopses as 200-dimensional semantic vectors, paired with Cosine similarity to measure the closeness between a user's free-text keyword and movie synopses without requiring a seed movie. Data were split using an 80:20 Holdout method, and algorithm performance was evaluated on a Top-3 Recommendation window using Precision@K, Recall@K, and Mean Reciprocal Rank (MRR), with ground truth validated by two experts through Inter-Annotator Agreement. Testing on 25 queries produced a Precision@3 of 0.5333, Recall@3 of 0.7800, and MRR of 0.7300. These results indicate that integrating word embeddings with web scraping yields semantically relevant movie recommendations from free keyword input, though comparisons with baseline methods are needed for more definitive performance claims

Downloads

Download data is not yet available.

References

[1] S. Badugu and R. Manivannan, "K-Nearest Neighbor and Collaborative Filtering-Based Movie Recommendation System," in Comput. Networks Inventive Commun. Technol., LNDECT, vol. 141, Singapore: Springer, 2023, pp. 461–474, https://doi.org/10.1007/978-981-19-3035-5_35.

[2] D. P. Kumar et al., "Content Based Recommendation System on Movies," in Proc. Int. Conf. Emerging Trends Eng. (ICETE 2023), 2023, pp. 462–472, https://doi.org/10.2991/978-94-6463-252-1_49.

[3] Z. Yao, "Review of Movie Recommender Systems Based on Deep Learning," in Proc. ICLCC 2023, 2023, p. 02010, https://doi.org/10.1051/shsconf/202315902010.

[4] L. Romero Meza and G. D'Urso, "Filter bubble and Recommendation," Psychol. Stud. (Mysore), vol. 69, no. 3, pp. 349–367, 2024, https://doi.org/10.1007/s12646-024-00807-0.

[5] D. Velamentosa and E. Zuliarso, "Sistem Rekomendasi Film Menggunakan Metode Content-based filtering," JATI, vol. 9, no. 2, pp. 2918–2922, 2025, https://doi.org/10.36040/jati.v9i2.13251.

[6] S. Sinha and T. Sharma, "Content-Based Movie Recommendation System: An Enhanced Approach," Int. J. Innov. Res. Comput. Sci. Technol., vol. 11, no. 3, pp. 67–71, 2023, https://doi.org/10.55524/ijircst.2023.11.3.12.

[7] H. Yuan and A. A. Hernandez, "User Cold Start Problem in Recommendation Systems: A Systematic Review," IEEE Access, vol. 11, pp. 136958–136977, 2023, https://doi.org/10.1109/ACCESS.2023.3338705.

[8] I. Valova, T. Mladenova, G. Kanev, and T. Halacheva, "Web Scraping - State of Art, Techniques and Approaches," in Proc. Natl. Conf. Int. Participation TELECOM, 2023, pp. 1–4, https://doi.org/10.1109/TELECOM59629.2023.10409723.

[9] C. Mediani et al., "Content-Based Recommender System using Word Embeddings for Pedagogical Resources," in Proc. Int. Conf. Pattern Anal. Intell. Syst. (PAIS), 2023, pp. 1–8, https://doi.org/10.1109/PAIS60821.2023.10321989.

[10] S. J. Johnson, M. R. Murty, and I. Navakanth, "A detailed review on word embedding techniques with emphasis on word2vec," Multimed. Tools Appl., vol. 83, no. 13, pp. 37979–38007, 2024, https://doi.org/10.1007/s11042-023-17007-z.

[11] X. Tian, "Content-based Filtering for Improving Movie Recommender System," in Proc. DAI 2023, Atlantis Press, Feb. 2024.

[12] F. Yang, H. Dong, W. Wang, W. Ding, and T. Lin, "A Comprehensive Survey on Inter-Annotator Agreement and the Use of Cohen's Kappa and Fleiss' Kappa for Ground Truth Validation in AI Algorithm Evaluation," IEEE Access, vol. 11, pp. 21300–21312, 2023, https://doi.org/10.1109/ACCESS.2023.3249759.

[13] A. Kumar and R. Singh, "BERT-Based Semantic Movie Recommendation Using Synopsis Embeddings," J. Inf. Sci. Eng., vol. 40, no. 2, pp. 341–358, 2024, https://doi.org/10.6688/JISE.202403_40(2).0007.

[14] F. Zhang, Y. Liu, and H. Chen, "Hybrid Movie Recommendation Integrating Metadata and Contextual Embeddings," IEEE Access, vol. 12, pp. 15234–15248, 2024, https://doi.org/10.1109/ACCESS.2024.3358921.

[15] I. Prasetya and D. Santoso, "Indonesian-Language Keyword-Based Content Retrieval on Multilingual Film Datasets," J. RESTI, vol. 8, no. 1, pp. 112–121, 2024, https://doi.org/10.29207/resti.v8i1.5217.