With the rapid growth of e-books and e-libraries, it becomes difficult for people to find right books from the flood of information. Personalized recommender system has been developed to help users to find appropriate...
详细信息
ISBN:
(纸本)9791188428106
With the rapid growth of e-books and e-libraries, it becomes difficult for people to find right books from the flood of information. Personalized recommender system has been developed to help users to find appropriate books based on user' ratings and interests. Most of the existing book recommender systems are based on content-based or collaborative filtering algorithms. However, those recommender systems provide book recommendations only based on books' contents and users' personal interests. This paper proposes a hybrid personalized book recommender system which combines both book popularity and personalized interests to recommend books for users. Book popularity is identified by the collected tweets to indicate current reading trends. The book popularity is represented by Lucene score of each book based on the collected tweets. The proposed book recommender system combines model-based recommenderalgorithms such as item-based and Alternating Least Squares (ALS) with book popularity. A scalable architecture using big data framework is developed to ingest, store, process and analyze both batch and streaming data. Open-source big data tools such as Apache Solr, Apache Kafka, and Apache Spark MLlib are used to implement the proposed hybrid book recommender system. PySpark is used to implement data pre-processing and big data analysis. The ALS recommenderalgorithm is implemented by using Apache Spark MLlib. The results show that the accuracy of the proposed hybrid book recommender system is acceptable.
Recommendation system (RS) is a technology that provides accurate recommendations to users. However, it is not comprehensive to only consider the accuracy of the recommendation because users have different requirement...
详细信息
Recommendation system (RS) is a technology that provides accurate recommendations to users. However, it is not comprehensive to only consider the accuracy of the recommendation because users have different requirements. To improve the comprehensive performance, this paper presents a hybrid recommendation model based on many-objective optimization, which can simultaneously optimize the accuracy, diversity, novelty and coverage of recommendation. This model enhances the robustness of recommendations by mixing three different basic recommendation technologies. Additionally, we solve it with many-objective evolutionary algorithm (MaOEA) and test it extensively. Experimental results demonstrate the effectiveness of the presented model, which can provide the recommendations with more and novel items on the basis of accurate and diverse. (C) 2020 Elsevier Ltd. All rights reserved.
暂无评论