Calkin A.S. Montero(1), Yukio Osawa(2),(3), and Kenji Araki(1)
(1)Graduate School of Information Science and Technology, Hokkaido University, Japan
(2)Graduate School of Business Science, University of Tsukuba, Japan
(3)Graduate School of Information Science and Technology, The
University of Tokyo, Japan
The ubiquity of chance discovery can be seen in many areas of application, fundamentally when there are events that are difficult to find or predict. In this paper, we present our idea of applying a chance discovery tool, the KeyGraph, for identifying relationship of co-occurrence between the utterances of the interlocutors during a chat section.