Neural network based stereotyping for user profiles

This paper discusses an approach of establishing system models of users' ta sk related characteristics, such as domain knowledge in human-computer inte raction. Several neural networks are tested for the modelling process. Thes e networks function as associative memories that capture the causal relatio nships among assumptions about the users' characteristics. The outputs from the networks are considered as stereotypes assigned to individual users. I t is suggested that this approach can be expected to overcome some limitati ons of user modelling approaches in terms of pattern recognition and classi fication.