Book Recommender System using Convolutional Neural Network
Authors:
- 23 November 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
The use of technology cannot be avoided along with the times. Searching, reading, and buying books online is one of the uses of technology. Several online book websites have provided free and paid online book services to users, such as gramedia.com, openlibrary.org, etc. Books available on online services have various types and ratings, depending on user interests. However, some book enthusiasts sometimes find it difficult to find other books that match their desires. Book recommender systems have been widely developed by utilizing collaborative filtering. However, collaborative filtering still leaves problems in terms of scalability and sparsity. To overcome this problem, we propose an approach for utilizing the Convolutional Neural Network (CNN) algorithm in a book recommender system. CNN has advantages in solving large data problems (scalability) and sparsity problems. We use book recommendation dataset from GitHub. To evaluate system performance, we combine several parameters, such as filter size, kernel size, and epoch. The best model is obtained by a combination of parameters with filter size of 8, kernel of 2, and epoch of 50 with MAE, MAPE, and MSE values are 1.361, 23,766, and 3,034, respectively.Keywords
This publication has 14 references indexed in Scilit:
- Collaborative Filtering for Book Recommendation System2019
- Online Book Recommendation System using Collaborative Filtering (With Jaccard Similarity)Journal of Physics: Conference Series, 2019
- A Time‐Aware CNN‐Based Personalized Recommender SystemComplexity, 2019
- Convolutional neural networks: an overview and application in radiologyInsights into Imaging, 2018
- Recommendation system techniques and related issues: a surveyInternational Journal of Information Technology, 2018
- A Recommendation Model Based on Deep Neural NetworkIEEE Access, 2018
- Neural Collaborative Filtering2017
- A fully convolutional neural network based structured prediction approach towards the retinal vessel segmentation2017
- Factors Influencing User’s Adoption of Conversational Recommender System Based on Product Functional RequirementsTELKOMNIKA (Telecommunication Computing Electronics and Control), 2016
- Design of knowledge for conversational recommender system based on product functional requirements2016