Abstract
Reading books is one of the widely-adopted methods to obtain knowledge. Through reading books, one can obtain life-long knowledge and maintain them. Additionally, if multiple sources of information can be obtained from various books, then obtaining relevant books is desirable. This can be done by book recommendation. There are, however, a number of challenges in designing a book recommender system. One of the challenges is to suggest relevant books to users without accessing their actual content. Unlike websites or blogs, where the crawler can simply scrape the content and index the websites for web search, book contents cannot be accessed easily due to copyright laws. Because of this problem, we have considered using data such as book records, which contains various metadata of a book, including book description and headings. In this paper, we propose an elegant and simple solution to the book recommendation problem using a deep learning model and various metadata that can infer the content and the quality of books without utilizing the actual content. Metadata, which include Library Congress Subject Heading (LCSH), book description, user ratings and reviews, which are widely available on the Internet. Using these metadata are relatively simple compared to approaches adopted by existing book recommender systems, yet they provide essential and useful information of books.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
An error is the relative divergence of the produced output from the ground truth.
- 2.
- 3.
A one-hot encoding of an integer value i among n unique values is a binarized representation of that integer as an n-dimensional vector of all zeros except the \(i^{th}\) element, which is a one.
- 4.
- 5.
Words within the Wikipedia documents were stemmed and stopwords were removed.
- 6.
- 7.
SentiWordNet, a lexical resource for opinion mining, assigns to each word in WordNet three sentiment scores: positivity, objectivity (i.e., neutral), and negativity. A SentiWordNet score is bounded between −1 and 1, inclusively.
- 8.
If a user does not offer a user profile P, then we simply treat the book provided by the user as the only book in P.
- 9.
- 10.
Other datasets can be considered as long as they contain user_IDs, book ISBNs, and ratings.
- 11.
The system was originally designed to predict ratings on movies but was implemented by [9] for additional comparisons on books as well.
- 12.
- 13.
References
Aslam, J., Montague, M.: Models for metasearch. In: ACM SIGIR, pp. 267–276 (1997)
Ding, Z.: The development of ontology information system based on Bayesian network and learning. In: Jin, D., Lin, S. (eds.) Advances in Multimedia, Software Engineering and Computing. Advances in Intelligent and Soft Computing, vol. 129, pp. 401–406. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-25986-9_62
Elmer, E.: Rasmuson Library. University of Alaska Fairbanks, Library of Congress Subject Headings (2014). https://library.uaf.edu/ls101-lc-subject
Givon, S., Lavrenko, V.: Predicting social-tags for cold start book recommendations. In: ACM RecSys. pp. 333–336 (2009)
Kleibergen, F., Paap, R.: Generalized reduced rank tests using the singular value decomposition. Econometrics 133(1), 97–126 (2006)
Linden, G., Smith, B., York, J.: Amazon.com recommendations: item-to-item collaborative filtering. Internet Comput. 7(1), 76–80 (2003)
Mooney, R., Roy, L.: Content-based book recommending using learning for text categorization. In: ACM DL 2000, pp. 195–204 (2000)
Owusu-Acheaw, M., Larson, A.: Reading habits among students and its effect on academic performance: a study of students of Koforidua Polytechnic. LPP 1130 (2014)
Qumsiyeh, R., Ng, Y.: Predicting the ratings of multimedia items for making personalized recommendations. In: SIGIR, pp. 475–484 (2012)
Ricci, F., Rokach, L., Shapira, B., Kantor, P.: Recommender System. Handbook. Springer, Cham (2011). https://doi.org/10.1007/978-3-319-29659-3
Shi, Y., Larson, M., Hanjalic, A.: Mining mood-specific movie similarity with matrix factorization for context-aware recommendation. In: Workshop on CARS, pp. 34–40 (2010)
Siersdorfer, S., Chelaru, S., Nejdl, W., Pedro, J.: How useful are your comments: analyzing and predicting YouTube comments and comment ratings. In: WWW, pp. 891–990 (2010)
Singh, A., Gordon, G.: Relational learning via collective matrix factorization. In: ACM SIGKDD, pp. 650–658 (2008)
Sohail, S., Siddiqui, J., Ali, R.: Book recommendation system using opinion mining technique. In: IEEE ICACCI, pp. 1609–1614 (2013)
Yang, C., Wei, B., Wu, J., Zhang, Y., Zhang, L.: CARES: a ranking-oriented CADAL recommender system. In: JCDL, pp. 203–212 (2009)
Yu, K., Zhu, S., Lafferty, J., Gong, Y.: Fast nonparametric matrix factorization for large-scale collaborative filtering. In: ACM SIGIR, pp. 211–218 (2009)
Zhu, Z., Wang, J.: Book recommendation service by improved association rule mining algorithm. In: ICMLC, pp. 3864–3869 (2007)
Ziegler, C., McNee, S., Konstan, J., Lausen, G.: Improving recommendation lists through topic diversification. In: WWW, pp. 22–32 (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Ng, YK., Jung, U. (2019). Personalized Book Recommendation Based on a Deep Learning Model and Metadata. In: Cheng, R., Mamoulis, N., Sun, Y., Huang, X. (eds) Web Information Systems Engineering – WISE 2019. WISE 2020. Lecture Notes in Computer Science(), vol 11881. Springer, Cham. https://doi.org/10.1007/978-3-030-34223-4_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-34223-4_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-34222-7
Online ISBN: 978-3-030-34223-4
eBook Packages: Computer ScienceComputer Science (R0)