Evaluation of Collaborative Filtering Based on Tagging with Diffusion Similarity Using Gradual Decay Approach

Abstract

The growth of the Internet has made difficult to extract useful information from all the available online information. The great amount of data necessitates mechanisms for efficient information filtering. One of the techniques used for dealing with this problem is called collaborative filtering. However, enormous success of CF with tagging accuracy, cold start user and sparsity are still major challenges with increasing number of users in CF. Frequently user’s interest and preferences drift with time. In this paper, we address a problem collaborative filtering based on tagging, which tracks user interests over time in order to make timely recommendations with diffusion similarity using gradual decay approach.