Collaborative Filtering using Tagging Information

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering

FYT Presentation and Demonstration

Title: "Collaborative Filtering using Tagging Information"

Miss WANG Nannan

Abstract

To improve the accuracy of recommender systems, tagging information can be
used to evaluate the similarity between users and items. With the help of
this additional information, a recently proposed method called tag informed
collaborative filtering (TagiCoFi) works better than its counterparts.
However, TagiCoFi only considers using tagging information to represent the
similarity between users. In this project, we study the behavior of TagiCoFi
and try to improve it by considering the similarity between items (movies)
as well as users represented by the tags. Experimental results show that
adding movie similarity can improve the original TagiCoFi to some extent and
the overall behavior is similar to that of the original version.


Date		:	14 May 2010 (Friday)

Time		:	9:30am to 10:10am

Venue		:	Room 4480

Advisor		:	Prof. D.Y. Yeung

2nd Reader	:	Prof. Yang Qiang, Prof. Nevin Zhang