August 2007
BCS IRSG Symposium: Future Directions in Information Access 2007 (FDIA)
Future Directions in Information Access
28-29 August 2007
Social Media, Personalization, Collaborative Tagging, Rating, Collaborative Filtering, Information Retrieval
This article describes a framework that captures collaborative tagging systems, and derives from it an overview of user tasks that qualify for personalization in such a system. Major research areas have focused on some of these tasks, but we identify many more opportunities. We propose a collaborative model that combines collaborative filtering and information retrieval techniques in order to assists the user to achieve these tasks. Based only on the user’s tags, this personalization model assumes that a user’s tags identify this user’s taste. Because many users do not only tag the content that matches their taste, we propose an evaluating experiment that shows if rating information can be used to adjust the users’ taste profiles. This experiment is one of the steps to advance to a completely personalized model, integrating user preference, content annotations and people relations.
This work is licensed under a Creative Commons Attribution 4.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/