Detecting Microstructures of Conversations Using Physical References of Posters as Contextual Data

The purpose of the work presented in this paper is reusing conversational archives. So far we have proposed a method to give structures to conversations by analyzing gaze and utterance data from an interaction corpus, which is a semi-structured set of a large amount of interaction data collected by various sensors. In this paper, we give more detailed structure to conversations by analyzing poster touch data. We devise a poster touch capturing method and investigate corelation between poster touch and conversation structure, that is to say, a topic of conversation has a relation to sub-theme in a poster that an exhibitor touched at at the time when it was made. By analyzing relation between conversations and poster touch data, we can get a transition of topics, and divide a long conversation which is made from many topics into some microstructured conversations which are made from one topic or context.