Research Topic: Info-bead User Modeling and Its Application in a Ubiquitous Cultural Heritage Environment.

Supervisor: Prof. Tsvi Kuflik.

User models (UMs) allow systems to provide personalized services to their users. Nowadays, UMs are developed ad-hoc, as part of specific applications, thus requiring repetitive development efforts. This study proposes the info-bead user modeling approach, which is based on ideas taken from software engineering in general and component-based software development in particular in order to standardize and ease user models development and deployment. The goal of the suggested approach is to ease the modeling process and to allow reuse of info-beads, developed for one UM, in other UMs that need the same information.

The concepts of the info-bead user modeling approach are presented through a bottom up buildup. The basic standalone unit, the info-bead, represents a single user attribute by handling instances of time-tagged information-items for this attribute. An info-bead encapsulates an inference process that uses data received from other info-beads or sensors to generate its information-items. Having standard interfaces (info-links), the info-beads can be composed as needed into complex and abstract user models (UMs) and group models (GMs).

As a test case for the assessment of the info-bead user modeling approach, we selected a ubiquitous user modeling case. Ubiquitous user modeling may be challenging because a ubiquitous computing environment requires inference from multiple sensors in a distributed deployment. Searching for an environment that would be ubiquitous, and would require the development of UMs and GMs, we found the museum environment challenging and enabling at the same time. Being able to detect the individual visitor behavior and the social behavior of a group of visitors, allows the implementation of UMs and GMs, hence, become an adequate test case for the info-bead user modeling approach.

For further assessment of the info-bead user modeling approach we demonstrate its ability to support also an ontology-based UM. For this purpose, an assistive technology UM, based on existing assistive technology ontology, was developed. Following that, students participating in a "Personal Adaptation of Information Systems to Users" course used the proposed approach. In addition, we analyzed and assessed the characteristics of the approach with respect to existing generic user modeling criteria, and compared it with other approaches.