Book Recommendation Using Machine Learning Methods Based on Library Loan Records and Bibliographic Information

Abstract

In this paper, we propose a method to recommend Japanese books to university students through machine learning modules based on several features, including library loan records. We determine the most effective method among the ones that used (a) a support vector machine (SVM), (b) a random forest, and (c) Adaboost. Furthermore, we assess the most effective combination of relevant features among (1) the association rules derived from library loan records, (2) book titles, (3) Nippon Decimal Classification (NDC) categories, (4) publication years, and (5) frequencies with which books were borrowed. We conducted an experiment involving 60 subjects who were students at T University. The books recommended by our candidate methods as well as the loan records used were obtained from the T University library. The results showed that books recommended by the method that employs an SVM based on features (2), (3), and (5) were rated most favorably by subjects. The method outperforms previous book recommendation techniques, such as that proposed by Tsuji et al. (2013), and is comparable in recommendation performance to the website Amazon.co.jp. The results obtained were independent of student grades, NDC categories, and the publication years of books.

The use of machine learning algorithms in recommender systems: A systematic review

“…Song et al, 2011;I. Song et al, 2011;Sun et al, 2015;Szabó et al, 2012;Szymański & Rzeniewicz, 2016;Takács et al, 2008;Takáes et al, 2009;Tsapatsoulis et al, 2015;Tsuji et al, 2014;Verma et al, 2016;Vialardi et al, 2011;Wan et al, 2009;Wang et al, 2012;Wei et al, 2011;Xin et al, 2014;Yan et al, 2013;Yap et al, 2005 Unsupervised learning 46 24 (Bar et al, 2013;Bjelica, 2010;Bouneffouf et al, 2012;Buettner, 2016;Degemmis et al, 2007;Devi & Venkatesh, 2013;Elmongui et al, 2015;Z. Fan et al, 2016;Ghazarian & Nematbakhsh, 2015;Halder et al, 2014;Hassan et al, 2010; T.-J.…”

Understanding Artificial Intelligence in Research Libraries – Extensive Literature Review

“…Bypassing librarians 4 Ewing & Hauptman, 1995;Gorichanaz et al, 2020;Nolin, 2013) No role 47 (e.g., Stehno & Retti, 2003;Wetzler et al, 2009) RQ 3 Role of non-humans AI-1 Tool/system 51 (e.g., Alexander et al, 2019;Baba et al, 2016;Iqbal et al, 2020;Jadhav & Shenoy, 2020;Kanarkard et al, 2017;Rubin et al, 2010;Schoeb et al, 2020;Tsuji et al, 2014 Benedetti et al, 2020;Finnemann, 2014;Lorang et al, 2020;Muehlberger et al, 2019;Nolin, 2013;Sidorko, 2009) AI-6…”

Book Recommendation to Wikipedia Article Readers in a University Library

“…(c-3) The author, together with others, has previously reported that the recommendation of frequently borrowed books produces better results [33]. To promote the recommendation of such books, the loan frequencies of the library books were adopted as a feature in the CNN and SVM, specifically the number of times that each book had been borrowed between January Copyright © by IIAI.…”

“…This particularly distinguishes the system from those of Mikawa et al [7] and Jomsri [8]. Other works on book recommendation systems include those of Mooney & Roy [9], Givon & Lavrenko [10], Yang et al [11], Pera et al [12], Crespo et al [13], Vaz et al [14], Benkoussas & Bellot [15], Pathak et al [16], Vaz et al [17], Garrido et al [18], Pera & Ng [19], Pera & Ng [20], Priyanka et al [21], Rajpurkar et al [22], Sase et al [23], Bhosale et al [24], Gao et al [25], Sohail et al [26], Alharthi et al [27], Parekh et al [28], Sohail et al [29], Thanapalasingam et al [30], Tsuji et al [31], Tsuji et al [32] and Tsuji et al [33]. However, the aims and target users of the systems developed in these previous works differ from those of the present study.…”