A Recommender System by Two-level Collaborative Filtering

X. Guo, J. Lu, and G. Zhang (Australia)

Keywords

Personalization, recommender system, collaborative filtering, web usage mining

Abstract

A vast of information and services on the web have caused the information overload problem. Search engines are pretty difficult to locate appropriate information due to the huge number of search results. In the last a few years, recommender system techniques have gained much attention. Most recommender systems adopt two types of techniques: content-based and collaborative filtering approach. In this study, a subject recommender system has been developed and implemented in an education environment. The system aims to locate right subject information to right students according to their individual needs and interests. With a technical advance, the system has integrated content-based, collaborative filtering and web usage analysis technique. Furthermore, we propose novel two-level collaborative filtering method in the system to improve the sparsity problem resolve at the early stages of recommender system.

Important Links:



Go Back


IASTED
Rotating Call For Paper Image