Communications of the ACM
Personalization on the Net using Web mining: introduction
Communications of the ACM
Explaining collaborative filtering recommendations
CSCW '00 Proceedings of the 2000 ACM conference on Computer supported cooperative work
Item-based collaborative filtering recommendation algorithms
Proceedings of the 10th international conference on World Wide Web
Mining web logs to improve website organization
Proceedings of the 10th international conference on World Wide Web
Using Sequential and Non-Sequential Patterns in Predictive Web Usage Mining Tasks
ICDM '02 Proceedings of the 2002 IEEE International Conference on Data Mining
SEWeP: using site semantics and a taxonomy to enhance the Web personalization process
Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining
A New Approach for on Line Recommender System in Web Usage Mining
ICACTE '08 Proceedings of the 2008 International Conference on Advanced Computer Theory and Engineering
| Hi-index | 0.00 |
Recommender systems are the software agents which are widely used to resolve the problem of information overload. These systems have become a key tool in e-Commerce activities because they have provided an added value to web based applications for the customer satisfaction. In this paper, an architectural framework of web personalization for hybrid recommender system i.e., Semantic Enhanced Personalizer (SEP) is proposed, which comprised of three techniques of recommendation such as, original recommendation, semantic recommendation and category based recommendation and it is compared with three frameworks of web personalization such as, Semantic Enhanced Web Personalizer (SEWeP), Online Recommendation in Web Usage Mining System(OLRWMS) and WEBMINER described on the basis of various parameters. It is observed that SEP is usage based personalization framework which focuses on online phase of recommendation strategies with maximum user preferences. The SEP overcomes the problems of existing recommender systems such as, cold-start, sparsity, scalability, quality of recommendation and synonymy using various data mining techniques such as association rule mining, clustering and similarity measures. It also recommends the multiple items with high accuracy and correctness, minimum response time, high quality and minimum false positive rates on the basis of implicit, explicit and contextual user preferences.