International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064 Index Copernicus Value (2013): 6.14 | Impact Factor (2014): 5.611 Volume 4 Issue 12, December 2015 www.ijsr.net Licensed Under Creative Commons Attribution CC BY Survey Paper on Website Recommendation System Using Browser History and Domain Knowledge Harshali Bendale 1 , H. A Hingoliwala 2 1 M.E (Computer) Department of Computer Engineering, Jayawantrao Sawant College of Engineering, Pune, India. Savitribai Phule Pune University, Pune, Maharashtra, India -411007 2 Head of Department and Asso. Prof(Computer) Department of Computer Engineering, Jayawantrao Sawant College of Engineering, Pune, India. Savitribai Phule Pune University, Pune, Maharashtra, India -411007 Abstract: With the rapid growth of internet technologies, the web has become the world's largest repository of knowledge. So it is challenging task of the webmasters to organize the contents of the particular websites to gather the needs of the users. This paper presents a new framework for a semantic-enhanced Web-page recommendation. This proposed system consists of three models. First two models represent the domain knowledge. The first model shows domain ontology of website. The second model build semantic network of website using domain terms, web pages and relations between them. The third model is personalized meta-search engine, help users to pick up the useful information for them quickly by using their interest keeping in the database. The proposed system automatically discovers and constructs the domain and Web usage knowledge bases, and generate effective Webpage recommendations. Keywords: semantic network, web page recommendation, domain ontology, meta search engine 1. Introduction As the World Wide Web continues to grow at an exponential rate, the size and complexity of many web sites grow along with it. For the users of these web sites it becomes increasingly difficult and time consuming to find the information they are looking for. User interfaces could help users find the information that is in accordance with their interests by personalizing a web site. Some web sites present users with personalized information by letting them choose from a set of predefined topics of interest. Users however do not always know what they are interested in beforehand and their interests may change overtime which would require them to change their selection frequently. Recommendation systems provide personalized information by learning the user’s interests from traces of interaction with that user. Web-page recommendation has proved in recent years to be a valuable means of helping Web users by providing useful and effective recommendations or suggestions. The core techniques in web-site recommendation are the learning and prediction models which learn user’s behavior and evaluate what users would like to view in the future. In particular, it can suggest interesting items from a large set of items based on the knowledge gained about an active user. Web-site recommendation can automatically recommend Web-sites that are most interesting to a particular user based on the user’s current Web navigation behavior. Good Web- site recommendations can improve website usage and Web user satisfaction. This proposed system presents a novel method to provide better Web-site recommendation based on browser history and domain knowledge, which is supported by three new knowledge representation models. The first model is an ontology based model that represents the domain knowledge of a website. Domain ontology specifies the terms and relationship between them explicitly and officially, which show the domain knowledge for specific domain. Ontologies are implemented in OWL. The second model is semantic network of website which shows domain terms, web pages and relations between them. Based on relations between terms and web pages, we can conclude how closely the web- pages are semantically related to each other. The third is personalized meta-search engine. Personalized meta-search engine is one search engine that we teach the machine to learn users' interest, so the search engine can help users to pick up the useful information for them quickly by using their interest keeping in the database. Personalized meta-search engine can sort the results according to user’s interest, the results that user likes will be the top of the results. 2. Literature Survey and Related Work How to make effective Web-page recommendations to Web users without excessive input from those users is a hot research topic. Significant effort has been devoted to developing effective Web-page recommender systems; however, a number of problems have been encountered in the development of existing Web-page recommender systems. “New page” problem Existing system [2] of Web-page recommendation uses tree structures and Web access sequences. If a user is visiting a Web-page that has not been accessed before, e.g. a newly- added Web-page, the user cannot obtain a recommendation. This phenomenon is often referred to as the “new page” problem. The reasons why such a phenomenon occurs are: (i) the recommendations are generated based on the recommendation rules obtained from the frequent Web access patterns discovered from the Web usage dataset; (ii) the new page is not included in the Web usage dataset so it Paper ID: NOV151843 659