Exploring the value of folksonomies for creating semantic metadata

Finding good keywords to describe resources is an on-going problem. Typically, we select such words manually from a thesaurus of terms, or they are created using autoinatic keyword extraction techniques. Folksonomies are an increasingly well-populated source of unstructured tags describing Web resources. This article explores the value of the folksonoiny tags as a potential source of keyword metadata by examining the relationship between folksonomies, community produced annotations, and keywords extracted by machines. The experiment has been carried out in two ways: subjectively, by asking two human indexers to evaluate the quality of the generated keywords from both systems; and automatically, by measuring the percentage of overlap between the folksonomy set and machine generated keywords set. The results of this experiment show that the folksonomy tags agree more closely with the human generated keywords than those automatically generated The results also showed that the trained indexers preferred the semantics of folksonomy tags compared to keywords extracted automatically. These results can be considered as evidence for the strong relationship of folksonomies to the human indexer mindset, demonstrating that folksonomies used in the del. icio. us bookmarking service are a potential source for generating semantic metadata to annotate Web resources.