Murdoch University Research Repository

Welcome to the Murdoch University Research Repository

The Murdoch University Research Repository is an open access digital collection of research
created by Murdoch University staff, researchers and postgraduate students.

Learn more

Typicality in computer mediated discussions - an analysis with neural networks

Berthold, M.R. and Sudweeks, F.ORCID: 0000-0003-0237-3671 (1995) Typicality in computer mediated discussions - an analysis with neural networks. In: IEEE International Conference on Neural Networks, 27 November - 1 December, Perth, Western Australia pp. 932-936.

Link to Published Version:
*Subscription may be required


ProjectH, a large group of international researchers, produced a huge amount of data from computer mediated discussions. The data classified several thousand postings from more than thirty newsgroups. One approach to extract typical messages from this database is presented in this paper. An autoassociative neural network was trained on 3000 coded messages and then used to construct typical message under certain specified conditions for several scenarios. This paper illustrates the architecture of the neural network that was used and explains the necessary modifications to the coding format. In addition several `typicality sets' produced by the neural net are shown and their generation is explained. In conclusion the ANN is used to explore the types of messages that typically initiate or contribute to longer lasting threads.

Item Type: Conference Paper
Publisher: IEEE
Item Control Page Item Control Page