Open AccessExploiting Visual Content of Book Front Cover to Aggrandize the Content Based Book Recommendation System
Author(s) -
Tulasi Prasad Sariki,
G. Bharadwaja Kumar
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.l3158.1081219
Subject(s) - recommender system , computer science , domain (mathematical analysis) , cover (algebra) , front cover , key (lock) , collaborative filtering , product (mathematics) , revenue , world wide web , information retrieval , content (measure theory) , engineering , mathematics , mechanical engineering , mathematical analysis , geometry , computer security , accounting , business
In modern e-commerce world Recommendation Systems are playing a key role in supporting customers to take a decision. With this kind of services customers can choose comfortably the products as per their preferences from a long list of available products. It’s not only a boon for the customers; it will boost the sales for the organization and generate better revenues. Due to diverse domain characteristics, each domain requires different kinds of recommendation models. Content based recommendation model is one of the recommendation models which purely rely on product features and the current user preferences. This model is more effective for the domains like news, micro-blogs, books, movie plots and scientific papers etc. In this paper we propose a content-based filtering model for book recommender system by utilizing its overall textual features as well as visual features of its front cover. Numerous surveys have demonstrated that book readers are highly inclined to its covers that are visually attractive1 . Book front cover is the first representative candidate of the book that will reveal the overall sense of the book; hence we considered book front cover as one of the book contents along with the text. Our experiment shows that augmenting the visual features to the existing content-based recommender models performed well.