Multi-Aspect Tagging for Collaborative Structuring

Abstract

Local tag structures have become frequent though Web 2.0: 
Users "tag" their data without specifying the underlying semantics. 
A collection of media items is tagged multiply using different aspects, 
e.g., topic, genre, occasion, mood. Given the large number of local, individual structures, users could benefit from the tagging work of others
 ("folksonomies"). In contrast to distributed clustering, no global structure
is wanted. Each user wants to keep the tags already annotated, wants to
keep the diverse aspects under which the items were organized, and only
wishes to enhance the own structure by those of others. 
A clustering algorithm which structures items has to take into account the 
local, multi-aspect nature of the task structures. 
The LACE algorithm (Wurst et al. 2006) is such a clustering algorithm.