A cognitive model of the web user

The present work describes a novel approach by applying a neurophysiological theory of decision making for describing web user browsing behavior. A dynamic stochastic model of the decision making process is proposed. Such a model is based on the Leaky Competing Accumulator (LCA) model of neurophysiology. It describes the neural activity of different brain regions during the subject resolution of the decision, by means of a stochastic process that evolves until an activity reaches a given threshold that fires the decision. Such a class of stochastic processes applied to decision making has been experimentally studied for nearly forty years. In this context, a web user is confronted with deciding which link to follow according to his/her own purposes, and the process is repeated again for each visited page until leaving the web site. The parameters of the model are adjusted by means of the maximum likelihood method, using the observed sequences of pages and the time spent on each of them. It has been observed that nearly 73% of the real distribution is recovered by this method.