TaxoFolk: A hybrid taxonomy-folksonomy structure for knowledge classification and navigation

With the emergence of Web 2.0, user-generated metadata or so-called folksonomies facilitates management of digital content in the World Wide Web. The folksonomies have increasingly become a viable alternative for knowledge seekers to classify their knowledge (resources) and navigate the resources. Traditionally, in expert systems, taxonomy has been fulfilling these roles. However, in a taxonomy, the taxonomic structures are defined by the taxonomists or professional experts of the domain which often do not reflect user vocabulary. In addition, the terms of the taxonomy become outdated very fast which in turn compromises the efficiency and effectiveness of knowledge classification and navigation. On the other hand, maintenance of the taxonomy is time consuming and exhausted. This paper presents taxonomy and folksonomy integration algorithm, namely TaxoFolk to integrate the folksonomy into a taxonomy to enhance knowledge classification and navigation. The output is a hybrid taxonomy-folksonomy structure. The TaxoFolk algorithm comprises of data mining techniques, namely formal concept analysis (FCA), ID3 classification and simple matching coefficients (SMC). Three different taxonomy domains and its folksonomy are used to setup the experiments to identify and to evaluate the threshold values for filtering infrequent tags and invalid tags to automate the TaxoFolk algorithm to integrate a filtered folksonomy with a pre-defined taxonomy for enhancing knowledge navigation. The conducted experiments have ascertained the most appropriate thresholds values for effective building of TaxoFolk structure.