Professional Documents
Culture Documents
Abstract: In addition to using the many conventional approaches for making recommendation
systems, this paper proposes a complementary recommendation methodology. It is focused on
book recommendation. It proposes to make a comprehensive data repository of existing books,
available at the level of the user (in a library or a personal bookshelf). Further, by retrieving web
reviews of available books and new books by using existing web services, an infrastructure has
been developed for need-based book recommendation system. Implementation results show that
our book recommendation allows a user to eliminate irrelevant books and presents the desired
books to the user from given book set. The proposed book recommender is one of the first
systems in terms of focusing on meeting individuals’ needs rather than calculating similarity or
preferences automatically, which is adopted by the traditional recommender system.
Reference to this paper should be made as follows: Kuroiwa, T. and Bhalla, S. (2010) ‘Book
recommendation system for utilisation of library services’, Int. J. Computational Science and
Engineering, Vol. 5, Nos. 3/4, pp.207–213.
Biographical notes: Takanori Kuroiwa obtained his Master’s degree (2008) from University of
Aizu. His research interest includes data mining.
Subhash Bhalla is a Professor at the Graduate School of Computer Science and Engineering,
University of Aizu. He obtained his PhD from the Indian Institute of Technology, Delhi in 1984.
His research interests include distributed systems, real-time operating systems and distributed
information systems.
Figure 1 System architecture et al., 2003a, 200b). The book rating approach given by the
following formula depends not on the score of each book
but on the context of each book review.
N p − Nn
r= × ( rave − 1) + rave (1)
N p + Nn
system searches the KB by using a user’s first need (that is, activities. When a user requests to browse recommended
for example, a representative keyword such as ‘XML’) and books from given book set (such as other user’s library), the
book titles containing the keyword are retrieved. Then, the recommender system searches the web reviews using web
system automatically assembles the query to search web services and presents the selected books (that meet his/her
reviews by combining a selected book title and the user’s needs) to him/herself. The implementation details and
next need ‘easy’. By using Yahoo!/Technorati Web Service, results are discussed in the next section.
short summaries containing the assembled query are
extracted from retrieved web pages/blogs. Finally, the
extracted summaries are presented to the user. 5 Implementation details
A prototype system was implemented on Windows 2000
4.3 Book recommendation using Apache 2.0.5 and PHP 5.1.4. To test our book
After retrieving the web reviews according to the above recommendation facility, we collected 100 books from
method, our book recommender system presents Amazon.com. Assume that a user has registered his/her
recommended books to a user one by one according to needs like ‘database’, ‘good’ and ‘easy’. Also, note that the
Amazon.com’s sales rank. Currently, the web review top three pages of Yahoo!/Technorati search are retrieved as
retrieval and recommended book presentation are performed web reviews of a selected book.
in real-time. In other words, a user can trigger those two
Figure 6 to 9 show the recommended books and the review existing web service integration contributes to retrieving
comments retrieved by Yahoo! Web Service. Most reviews book reviews available on the web and corresponding the
are from Amazon.com related sites. This is because blog web reviews with each user’s needs. This recommendation
search results have not been taken into account. Technorati method is not an alternative approach to traditional
API (that is used for retrieving book reviews from blogs) is approaches such as the collaborative filtering and
unsuitable for retrieving web contents written in space the content-based approaches, but a complementary
delimited language like English because it does approach to such approaches. We believe the proposed book
not support a perfect matching search (at this time). recommender is one of the novel systems in terms of taking
However, it is appropriate for retrieving Japanese contents. users’ needs directly into consideration and focusing on
Therefore, we apply Technorati API to Japanese book meeting the needs rather than automatically predicating
review retrievals. recommended books, as in the case of the traditional
recommender systems.
For future work, we will investigate the following
things: coordination with traditional recommendation
6 Summary and conclusions
approaches and web review clustering to automatically
This paper proposed a need-based book recommendation classify web reviews into the positive ones and the negative
using web reviews. Implementation results show that ones.
Book recommendation system for utilisation of library services 213