Searching Similar Books Based on Student’s Preference for Personalized Education

Abstract

Abstract:Personalized education aims to give students a personalized learning schedule according to students' backgrounds and preferences, and the required learning resources for learning are personalized. On-line bookstore allows students to collect learning recourses on-line through Internet, but the problem of information overload plagues students since it is difficult to find the suitable books with the data becoming diverse and massive. Similarity search aims to find the similar objects to a given query, which can be regarded as a promising solution to the problem of information overload. However, the existing similarity search approaches limit the query into only one object, the students cannot express their preferences personally. In this paper, we proposed a personalized similarity search framework, towards finding the similar books based on student's preference for personalized education. We build the student-book network based on the students' ratings for books, and use SimRank to measure the similarities between books according to the student-book network. For satisfying student's personalized query preference, we allow student to express query with multi-books. A personalized similarity measure is proposed for measuring the similarity between query and candidate book by combining the similarities between books. Experiments on Amazon dataset demonstrate that, when the number of input books are not limited into one, the returned rankings are more consistent with students' query intentions.

Research on Personalized Book Recommendation Based on Improved Similarity Calculation and Data Filling Collaborative Filtering Algorithm

“…e higher the F-measure value, the higher the effectiveness of the algorithm. e F-measure calculation formula is shown in (3)- (4).…”

“…With the rapid development of cloud computing, Internet of Things, Internet and other technologies and Web 2.0, in many scenarios such as the network and digital libraries [ 1 – 3 ], a large amount of information data is constantly emerging from book resources, which increases people's access to the required book information difficulty, resulting in ‘information overload [ 4 , 5 ]. How to solve the ‘information overload' and help users quickly find the book resources that meet their individual demand is an urgent problem to be solved [ 6 , 7 ], because book recommendation algorithms can realize ‘one-to-one' service according to users' personal preferences, to provide users with personalized services book recommendations.…”