Exploration of applying a theory-based user classification model to inform personalised content-based image retrieval system design

To better understand users and create more personalised search experiences, a number of user models have been developed, usually based on different theories or empirical data study. After developing the user models, it is important to effectively utilise them in the design, development and evaluation of search systems to improve users’ overall search experiences. However there is a lack of research has been done on the utilisation of the user models especially theory-based models, because of the challenges on the utilization methodologies when applying the model to different search systems. This paper explores and states how to apply an Information Foraging Theory (IFT) based user classification model called ISE to effectively identify user’s search characteristics and create user groups, based on an empirically-driven methodology for content-based image retrieval (CBIR) systems and how the preferences of different user types inform the personalized design of the CBIR systems.