Folksonomies and clustering in the collaborative system CiteULike

TL;DR

This paper analyzes the semantic relationships in CiteULike, a collaborative tagging system, revealing how clustering coefficients can improve data classification and spam detection.

Contribution

It introduces a graph-based approach to study tag semantics and demonstrates how clustering coefficients reflect meaningful semantic patterns.

Findings

Clustering coefficient indicates semantic patterns among tags

Semantic relationships can enhance data classification

Clustering metrics assist in spam detection

Abstract

We analyze CiteULike, an online collaborative tagging system where users bookmark and annotate scientific papers. Such a system can be naturally represented as a tripartite graph whose nodes represent papers, users and tags connected by individual tag assignments. The semantics of tags is studied here, in order to uncover the hidden relationships between tags. We find that the clustering coefficient reflects the semantical patterns among tags, providing useful ideas for the designing of more efficient methods of data classification and spam detection.