Human dialogue is so complex that definitively analysing patterns of conversation may well be impossible. Within a conversation, all the complexities and ambiguities of natural language exist and each speaker will have his/her own speech characteristics and moods. Examining these characteristics through text dialog can be a demanding cognitive task. One reason is because the whole conversation cannot be viewed at one time. This task can be made more convenient if there is a way of visualising all this information at once through graphical patterns. Graphical patterns can revolve around the conversation, creating an abstract piece of artwork. From these patterns, one can guess at the speaker’s emotion and how he/she is connected to another speaker during a conversation. This paper will discuss the different visualisation techniques that are used to represent several aspects of a conversation.
Download video (14.6 MB)
|A. Tat and M.S.T. Carpendale. Visualizing Human Dialog. In Proceedings of IEEE Conference on Information Visualization IV’02, pages 16-24, 2002.|
This work is part of 3D Web and is partially supported by grants from Heritage Canada, Intel, Canadian Foundation for Innovation, the Natural Sciences and Engineering Research Council of Canada, and the University of Calgary.