Adaptive Hypermedia 2008
Program  > 31 July (Thu)  > DC: User Models and Collaboration 
Doctoral Consortium: User Models and Collaboration

Thursday 31 July, 16:00 - 17:30

Adaptive User Modelling and Recommendation in Constrained Physical Environments (page 378)

Fabian Bohnert

Visitors to physical educational environments, such as museums, are often overwhelmed by the information available in the space they are exploring. They are confronted with the challenge of finding personally interesting items to view in the available time. Electronic mobile guides can provide guidance and point to relevant information by identifying and recommending items that match a visitor’s interests. However, recommendation generation in physical spaces has challenges of its own. Factors such as the spatial layout of the environment and suggested order of item access must be taken into account, as they constrain the recommendation process. This research investigates adaptive user modelling and personalisation approaches that consider such and other constraints.

Facilitating Collaboration in Virtual Environments (page 389)

Diana Chihaia

The evolution of learning systems brought improvements to the functionality of their components by offering support and mediating learning, communication and collaboration. However, there are still existing barriers caused by the lack of face to face contact between users. Through our research we aim to provide novel means for supporting the social cohesion of the groups and personalize the e-learning spaces by offering adaptive support in group forming and collaboration processes. As a first step in designing a filtering tool for an adaptive system which recommends application and activities for collaboration within the group, we designed a series of experimental studies on different components of an e-learning system to find out what initiates, influences and increases the level of collaboration between learners.

A Scrutable User Modelling Infrastructure for Enabling Life-Long User Modelling (page 421)

Demetris Kyriacou

User Modelling is the core component for the majority of personalisation systems. By keeping a model for every user, a system can successfully personalise its content and utilise available resources accordingly. While researching the literature, one can recognize the importance of achieving interoperability across various platforms and systems while attempting to personalise a large diversity of web resources. Furthermore, scrutable solutions allow users to control any modelling process that uses their information. Finally, privacy of user data while exchanging user models from one source to another must be taken in mind. With this paper, a Scrutable User Modelling Infrastructure is presented which blends together these user modelling ‘ingredients’ and, by adopting Semantic Web technologies, attempts to model a range of life-long user interactions with a variety of web-based systems from the educational, business and social networking domains.
User Modeling Inc. Leibniz University Hanover L3S Research Center Adaptive Hypermedia 2008 Conference Website
Eelco Herder (L3S Research Center, Hannover, Germany)