An Interactive Tool for Constrained Clustering with Human Sampling

This paper describes an interactive tool for constrained clustering that helps users to select effective constraints efficiently during the constrained clustering process. This tool has some functions such as 2-D visual arrangement of a data set and constraint assignment by mouse manipulation. Moreover, it can execute distance metric learning and k-medoids clustering. In this paper, we show the overview of the tool and how it works, especially in the functions of display arrangement by multi-dimensional scaling and incremental distance metric learning. Eventually we show a preliminary experiment in which human heuristics found through our GUI improve the clustering. This study provides fundamental technologies for interactive clustering of Web page and Web usages.