Users are individuals: individualizing user models
International Journal of Human-Computer Studies - Special issue: 1969-1999, the 30th anniversary
Machine Learning
Advertising in a pervasive computing environment
WMC '02 Proceedings of the 2nd international workshop on Mobile commerce
Ontology-based personalized search and browsing
Web Intelligence and Agent Systems
| Hi-index | 0.00 |
User profiling is commonly used to support personalization as well as to enhance usability of software systems by automatically adapting to the needs and preferences of their users. This paper presents an approach to dynamically update mobile users' profiles so that they can be provided with appropriate services while moving from one location to another. We propose an XML generic user profile structure that is dynamically updatable as the user experiences new services and that can be used by different software systems and applications. The proposed profile learning mechanism makes use of clustering users with a subset of similar attributes to predict appropriate services to a new user, and segmenting services with a subset of similar usage to discover and recommend new services that might be of interests to a mobile user. We demonstrated the feasibility of our approach by presenting a case study in tourism where tourists are assisted during their travels by providing them with services and information of interest. The tourist preferences and her/his current location are incorporated in the proactive formulation of suggestions on the tourist mobile devices about nearby points of interests (e.g. museums, restaurants...).