Gender-Biased Adaptations in Educational Adaptive Hypermedia

Studies (for instance, [1, 2]) show that there is a statistically relevant gender difference in computer usage. In this paper we address the question of what are the causes of this problem and how it can be relieved by adaptive means. In trying to design systems that are sensitive to individual differences there is a dilemma – how can you make the system behave in a way appropriate for each individual without forcing people into stereotypes? We propose that the group characteristics can be taken as weak defaults and coupled with an adaptive mechanism to quickly take account of individual differences. This paper starts with a summary of a study which derives a model of the mental factors that influence computer usage. Then, we refine that model and make it the basis of a Bayesian Net student model. The main section describes suggestions for Adaptive Hypermedia targeting the relevant mental factors and how adaptivity can help to avoid clichés and thus discrimination.