Exploiting Tag Relations to Improve Search in Collaborative Tagging Systems

The main problem of tag-based search in collaborative tagging system (CTS) is the lack of explicit semantic relations between tags. To address this problem, we propose an approach based on the integration of symmetrical and asymmetrical similarity measures to calibrate the relatedness between tags and then further organize them into an ontological structure. We also demonstrate how this extracted knowledge will help to apply semantic web techniques to existing web2.0 applications such as CTS and improve their search and browse capabilities.