An Efficient Web Personalization Approach to Discover User Interested Directories

Web Usage Mining is the application of data mining technique used to retrieve the web usage from web proxy log file. Web Usage Mining consists of three major stages: preprocessing, clustering and pattern analysis. This paper explains each of these stages in detail. In this proposed approach, the web directories are discovered based on the user's interestingness. The web proxy log file undergoes a preprocessing phase to improve the quality of data. Fuzzy Clustering Algorithm is used to cluster the user and session into disjoint clusters. In this paper, an effective approach is presented for Web personalization based on an Advanced Apriori algorithm. It is used to select the user interested web directories. The proposed method is compared with the existing web personalization methods like Objective Probabilistic Directory Miner (OPDM), Objective Community Directory Miner (OCDM) and Objective Clustering and Probabilistic Directory Miner (OCPDM). The result shows that the proposed approach provides better results than the aforementioned existing approaches. At last, an application is developed with the user interested directories and web usage details.