Semi-Automatic Online Tagging with K-Medoid Clustering

Abstract

Online tagging is crucial for the acquisition and organization of web knowledge. We present TYG (Tag-as-You-Go) in this paper, a web browser extension for online tagging of personal knowledge on standard web pages. We investigate an approach to combine a K-Medoidstyle clustering algorithm with the user input to achieve semi-automatic web page annotation. The annotation process supports user-de¯ned tagging schema and comprises an automatic mechanism that is built upon clustering techniques, which can automatically group similar HTML DOM nodes into clusters corresponding to the user speci¯cation. TYG is a prototype system illustrating the proposed approach. Experiments with TYG show that our approach can achieve both e±ciency and e®ectiveness in real world annotation scenarios.