Typicality in computer mediated discussions-an analysis with neural networks

Project H, 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 messages 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