Issues and Requirements for Successful Integration of Semantic Knowledge in Web Usage Mining for Effective Personalizati
Recommendation systems have been successfully used by e-commerce and other similar sites for recommendation of relevant items to the user. However majority of these systems are based on web usage mining which does not consider the semantic knowledge under
- PDF / 255,061 Bytes
- 7 Pages / 439.37 x 666.14 pts Page_size
- 48 Downloads / 194 Views
Department of Computer Science, Babasaheb Bhimrao Ambedkar University, Lucknow, India [email protected], [email protected]
Abstract. Recommendation systems have been successfully used by e-commerce and other similar sites for recommendation of relevant items to the user. However majority of these systems are based on web usage mining which does not consider the semantic knowledge underlying a website in the recommendation process and based solely on usage data. Hence researchers realized the importance of semantic knowledge and began to use it as part of usage data which is primarily used by personalization systems to enhance the quality of items being recommended. However several issues emerged during the process of integration. For effective personalization these issues need to be addressed. We discuss this aspect of inte‐ gration process and also suggest some of the ways to resolve these issues and also discuss few methods of representing domain knowledge under different situations. Keywords: Semantic knowledge · Web usage mining · Personalization · RDF
1
Introduction
Recommender Systems is software which is used to suggest the most relevant items to user from large database. Data mining plays a crucial role in their development. Web mining is the application of data mining on web logs, web content and web structures in order to find interesting patterns. Here we consider only the web usage mining as it is directly concerned to our topic. Web usage mining involves discovering user access patterns from log file. One of the applications of this is in an e-commerce where we may find a rule of the form X -> Y, which indicates that if a user has bought an item X then he is likely to buy item Y. The web usage mining is being used extensively in educational data mining such as recommending the best combination of courses to learners, offering ads, links and other resources. The web usage mining has few drawbacks as the recommendation is purely usage based and hence the new items added to the site recently cannot be recommended. Collaborative filtering approach is commonly used to deal with this problem [1, 12]. This is called keyword-based approach. However, the problem with this approach is that it is not able to capture more complex relationship that may exist among objects. Hence the semantic knowledge can help in recommending more complex objects, and this © Springer Nature Singapore Pte Ltd. 2016 A. Unal et al. (Eds.): SmartCom 2016, CCIS 628, pp. 97–103, 2016. DOI: 10.1007/978-981-10-3433-6_12
98
S.J. Dwivedi and B. Rawat
semantic knowledge needs to be combined at different stages of the web usage mining process. Here we first provide an overview of semantic web mining and presents its archi‐ tecture and then discuss different ways of representing domain knowledge and finally describe issues and requirements essential for semantic web usage mining.
2
Semantic Web Mining
Semantic web mining is the combination of two fast-developing research areas semantic web and web mining. We describe in Fig. 1 different layers
Data Loading...
