Affective reactions during human computer interaction seem to be more and more important for many e-commerce applications, including all kind of local and global reservation and booking systems. Understanding affective reactions is essential to improve the design of systems, to define interactive feedback or adaptation in system. The data collected are analysed not only to highlight affective reactions, but also to integrate hierarchical models of activity to study them, taking into consideration the context in which the user is at a given moment in the activity path. The preliminary results and the detailed methodology are mentioned within the paper.