Exploring temporal aspects in user-tag co-clustering

Tagging environments have become an interesting topic of research lately, focused mainly on clustering approaches, in order to extract emergent patterns that are derived from tag similarity and involve tag relations or user interconnections. Apart from tag similarity, an interesting parameter to be analyzed during the clustering/mining process in such data is the actual time that each tagging activity occurred. Indeed, holding a temporal dimension unfolds macroscopic and microscopic views of tagging, highlights links between objects for specific time periods and, in general, lets us observe how the users' tagging activity changes over time. In this article, we propose a time-aware user/tag clustering approach, which groups together similar users and tags that are very “active” during the same time periods. Emphasis is given on using varying time scales, so that we distinguish between clusters that are robust at many time scales and clusters that are somehow occasional, i.e. they emerge, only at a specific time period.