MOVIE RECOMMENDATION SYSTEM USING HYBRID FILTERING WITH WORD2VEC AND RESTRICTED BOLTZMANN MACHINES

Muhammad Aryuska Pradana
Agung Toto Wibowo


DOI: https://doi.org/10.29100/jipi.v9i1.4306

Abstract


Recommender systems are designed to provide interesting information to users and assist them in making choices. With the help of a recommender system, users can feel more comfortable using an application. In this final project, we will implement a hybrid filtering method using two techniques: Word2Vec as the algorithm for content-based filtering and Restricted Boltzmann Machine for collaborative filtering. The Word2Vec algorithm will utilize a pre-trained model provided by Google, while the Restricted Boltzmann Machine algorithm will utilize the TensorFlow library. The dataset used for this project will be Movie Lens. The goal of this final project is to evaluate the accuracy and performance of the recommender system using various metrics such as Precision and Normalized Discounted Cumulative Gain.


Keywords


Collaborative filtering; Content-based filtering; Hybrid filtering; Normalized Discounted Cumulative Gain; Precision; RBM; Restricted Boltzmann Machine; Word2Vec

Full Text:

PDF

Article Metrics :

References


Techlabs, Maruti. "How Can Product Recommendation System Benefit Your Business?" Medium, 25 Aug. 2021, medium.com/geekculture/how-can-product-recommendation-system-benefit-your-business-65afd9cabfd8. Accessed 22 Nov. 2022.

Singhal, Ayush, et al. "Use of Deep Learning in Modern Recommendation System: A Summary of Recent Works." International Journal of Computer Applications, vol. 180, no. 7, 2017, pp. 17-22.

A. Singhal, R. Kasturi, V. Sivakumar, and J. Srivastava, “Leveraging Web intelligence for finding interesting research datasets,” in Proceedings - 2013 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2013, 2013, vol. 1, pp. 321–328.

Isinkaye, F., Folajimi, Y., & Ojokoh, B. (2015). Recommendation systems: Principles, methods and evaluation. Egyptian Informatics Journal(16), 261– 273.

Isinkaye, F.O., et al. "Recommendation systems: Principles, methods and evaluation." Egyptian Informatics Journal, vol. 16, no. 3, 2015, pp. 261-273

Xiang, Z., & Gretzel , U. (2010, April). Role of social media in online travel information search. Tourism Management. (S. Page, Ed.) Tourism Management, 31(2), 179-188

Kotkov, Denis, et al. "Challenges of Serendipity in Recommender Systems." Proceedings of the 12th International Conference on Web Information Systems and Technologies, 2016.

Pazzani, Michael J., and Daniel Billsus. "Content-Based Recommendation Systems." The Adaptive Web, pp. 325-341.

Google Developers. "Content-based Filtering Advantages & Disadvantages | Machine Learning | Google Developers." Google Developers, 19 July 2022, developers.google.com/machine-learning/recommendation/content-based/summary

Gupta, Shraddha. "A Literature Review on Recommendation Systems." A Literature Review on Recommendation Systems , vol. 07, no. 09, Sept. 2022, p. 3602.

PineCode. "What Is Word2Vec?" Pinecone, www.pinecone.io/learn/roughly-explained/what-is-word2vec.

Gensim: topic modelling for humans. (2022, December 21). Models.Word2vec – Word2vec Embeddings &Mdash; Gensim. https://radimrehurek.com/gensim/models/word2vec.html

Fischer, A., & Igel, C. (2012). An Introduction to Restricted Boltzmann Machines. Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, 14–36. https://doi.org/10.1007/978-3-642-33275-3_2

Lops, P., de Gemmis, M., & Semeraro, G. (2010, October 5). Content-based Recommender Systems: State of the Art and Trends. Recommender Systems Handbook, 73–105. https://doi.org/10.1007/978-0-387-85820-3_3.

Dhinakaran, A. (2023, February 2). Demystifying NDCG. Medium. https://towardsdatascience.com/demystifying-ndcg-bee3be58cfe0