Design and Implementation of MapReduce-Based Book Recommendation System by Analysis of Large-Scale Book-Rental Data
We design and implement a book recommendation system that can extract and suggest the books preferred by users through keyword-matching based on the information of frequently checked out books. The MapReduce programming model on the Hadoop platform is use
- PDF / 447,618 Bytes
- 7 Pages / 439.37 x 666.142 pts Page_size
- 71 Downloads / 158 Views
Abstract We design and implement a book recommendation system that can extract and suggest the books preferred by users through keyword-matching based on the information of frequently checked out books. The MapReduce programming model on the Hadoop platform is used to extract frequently rented books by using keyword-mapping with a target book. The MapReduce operations designed and implemented in this paper are performed to analyze the actual book-rental log data accumulated in university library, which has the characteristics of big data. An illustrative example shows that our book recommendation system can provide users with the information of the recommended books by keyword-mapping in the next book rent. Keywords Book-rental
Recommendation MapReduce Hadoop Big data
1 Introduction Recently, big data processing and analysis have been actively achieved in various fields [1]. Since big data is unstructured and large-scale data, it is inadequate to be analyzed and processed by traditional computing systems and tools [1, 2]. The log data on rental books recorded in the electronic library of universities, one form of big data, includes various information on book-rental, such as users’ major and J.-M. Gil (&) D.-M. Seo School of Information Technology Engineering, Catholic University of Daegu, Gyeongbuk, South Korea e-mail: [email protected] D.-M. Seo e-mail: [email protected] J. Lim IT Convergence Education Center, Dongguk University, Seoul, South Korea e-mail: [email protected] © Springer Science+Business Media Singapore 2016 J.J. (Jong Hyuk) Park et al. (eds.), Advanced Multimedia and Ubiquitous Engineering, Lecture Notes in Electrical Engineering 393, DOI 10.1007/978-981-10-1536-6_93
713
714
J.-M. Gil et al.
interest, rental date, return date, keywords, etc. Such data are not only large-scale but also unstructured, making it difficult for them to be searched, managed, and stored via traditional relational databases and file systems. Moreover, the analysis and processing of book-rental data by traditional computing systems and tools are even more difficult. In general, it has a possibility that the frequently rented books have similar or the same keywords as the books that have previously rented. Based on this property, these books can be classified according to keywords; such the classification can be utilized to offer useful information for the next book rent. However, it is time-consuming and requires much effort to extract the meaningful patterns of rental books by matching the keywords of the books that have previously rented by users, due to a large volume of book-rental log data and its unstructured form. Therefore, we apply MapReduce programming model to analyze and process book keywords in book-rental big data and to classify highly related books with the information of frequently rented books by a user. To this end, we design and implement a book recommendation system that can extract and classify relevant books by keyword-matching. Eventually, the system provides users with book recommendation inform
Data Loading...
