UCASFUM: A Ubiquitous Context-aware Semantic Fuzzy User Modeling System

In this paper, we propose a ubiquitous user modeling system which illustrates different aspects of the individual’s interests and his/her current and future context. The user model is constructed by aggregating and semantically enhancing the partial profiles obtained by mining socially enhanced online traces of the user on a regular basis. Those traces include actions performed and relationships established in the social web accounts in addition to the local machine traces such as bookmarks and web history. The semantical enrichment process consists of two phases: constructing an overlay model by using concepts and hierarchical information from external knowledge bases and creating links from the constructed user model concepts to supported ontologies. The former phase outputs a semantically enhanced user model whereas the latter enables interoperability between applications which use the proposed system for personalization. Moreover, fuzzy membership values are computed for each interest and context item in the user model. In order to model the semantically enhanced user profile and represent fuzziness values, fuzzy hypergraph is used as data structure. Fuzzy hypergraph representation enables extraction of partial user profiles in the requested domains besides answering user modeling queries such as the degree of the user’s interest for the given concepts. By extracting partial profiles by specifying domains, the proposed system can be used for personalization purposes in multi application