Julita Vassileva

Course sequencing techniques for large-scale web-based education

We argue that traditional sequencing technology developed in the field of intelligent tutoring systems could find an immediate place in large- scale web-based education. This paper discusses two models that have been explored by the authors - the dynamic course generation system DCG and the concept-based course maintenance system CoCoA. DCG includes components for domain authoring and for automatic generation of adaptive courses on the WWW. It allows automatic generation of individualised courses according to the learners goal and previous knowledge, and can dynamically adapt the course according to the learners success in acquiring knowledge. . CoCoA can check the consistency and quality of a course at any moment of its life and also assists course developers in some routine operations.

Adaptive HyperText and Hypermedia

Preface. 1. Methods and Techniques of Adaptive Hypermedia P. Brusilovsky. 2. Adaptive Hypertext Navigation Based on User Goals and Context C. Kaplan, et al. 3. Metadoc: An Adaptive Hypertext Reading System C. Boyle, A.O. Encarnacion. 4. User Modelling in the Interactive Anatomy Tutoring System ANATOM-TUTOR I.H. Beaumont. 5. Hypadapter: An Adaptive Hypertext System for Exploratory Learning and Programming H. Hohl, et al. 6. A Glass Box Approach to Adaptive Hypermedia K. Hook, et al. 7. User-Centered Indexing for Adaptive Information Access N. Mathe, J.R. Chen. 8. A Task-Centred Approach for User Modeling a Hypermedia Office Documentation System J. Vassileva. Index.

Dynamic Courseware Generation on the WWW

We have developed a tool for the authoring of adaptive CAL courses, called “Dynamic Courseware Generator” (DCG). It generates an individual course according to the learners goals and previous knowledge and dynamically adapts the course according to the learners success in acquiring knowledge. The DCG runs on a WWW server. The learner receives from this server an individualized course targeted to a specified goal. Afterwards, s/he is adaptively guided by the course through a space of teaching materials on the WWW. Unlike other CAL courses on the WWW, a course produced by the DCG is interactive, it tests the learner’s knowledge and dynamically adapts to the students progress. The authoring tool can be used also for collaborative authoring and learning.

Toward Social Learning Environments

We are teaching a new generation of students, cradled in technologies, communication and abundance of information. The implications are that we need to focus the design of learning technologies to support social learning in context. Instead of designing technologies that ldquoteachrdquo the learner, the new social learning technologies will perform three main roles: 1) support the learner in finding the right content (right for the context, for the particular learner, for the specific purpose of the learner, right pedagogically); 2) support learners to connect with the right people (again right for the context, learner, purpose, educational goal etc.), and 3) motivate/incentivize people to learn. In the pursuit of such environments, new areas of sciences become relevant as a source of methods and techniques: social psychology, economic/game theory, multi-agent systems. The paper illustrates how social learning technologies can be designed using some existing and emerging technologies: ontologies vs. social tagging, exploratory search, collaborative vs. self-managed social recommendations, trust and reputation mechanisms, mechanism design and social visualization.

Bayesian network trust model in peer-to-peer networks

In this paper, we propose a Bayesian network-based trust model in peer-to-peer networks. Since trust is multi-faceted, even in the same context, peers still need to develop differentiated trust in different aspects of other peers’ behaviors. The peer’s needs are different in different situations. Depending on the situation, a peer may need to consider its trust in a specific aspect of another peer’s capability or in a combination of multiple aspects. Bayesian networks provide a flexible method to represent differentiated trust and combine different aspects of trust.

Design and evaluation of an adaptive incentive mechanism for sustained educational online communities

Most online communities, such as discussion forums, file-sharing communities, e-learning communities, and others, suffer from insufficient user participation in their initial phase of development. Therefore, it is important to provide incentives to encourage participation, until the community reaches a critical mass and “takes off”. However, too much participation, especially of low-quality can also be detrimental for the community, since it leads to information overload, which makes users leave the community. Therefore, to regulate the quality and the quantity of user contributions and ensure a sustainable level of user participation in the online community, it is important to adapt the rewards for particular forms of participation for individual users depending on their reputation and the current needs of the community. An incentive mechanism with these properties is proposed. The main idea is to measure and reward the desirable user activities and compute a user participation measure, then cluster the users based on their participation measure into different classes, which have different status in the community and enjoy special privileges. For each user, the reward for each type of activity is computed dynamically based on a model of community needs and an individual user model. The model of the community needs predicts what types of contributions (e.g. more new papers or more ratings) are most valuable at the current moment for the community. The individual model predicts the style of contributions of the user based on her past performance (whether the user tends to make high-quality contributions or not, whether she fairly rates the contributions of others). The adaptive rewards are displayed to the user at the beginning of each session and the user can decide what form of contribution to make considering the rewards that she will earn. The mechanism was evaluated in an online class resource-sharing system, Comtella. The results indicate that the mechanism successfully encourages stable and active user participation; it lowers the level of information overload and therefore enhances the sustainability of the community.

Multi-Agent Multi-User Modeling in I-Help

This paper describesthe user modeling approach applied in I-Help, a distributed multi-agent based collaborative environment for peer help. There is a multitude of user modeling information in I-Help, developed by the various software agents populating the environment. These ‘user model fragments’ have been created in a variety of specific contexts to help achieve various goals. They are inherently inconsistent with one another and reflect not only characteristics of the users, but also certain social relationships among them. The paper explores some of the implications of multi-agent user modeling in distributed environments.

A task-centered approach for user modeling in a hypermedia office documentation system

The development of user-adaptive systems is of increasing importance for industrial applications. User modeling emerged from the need to represent in the system knowledge about the user in order to allow informed decisions on how to adapt to match the users needs. Most of the research in this field, however, has been theoretical, “top-down.” Our approach, in contrast, was driven by the needs of the application and shows features of bottom-up, user-centered design.We have implemented a user modeling component supporting a task-based interface to a hypermedia information system for hospitals and tested it under realistic conditions. A new architecture for user modeling has been developed which focuses on the tasks performed by users. It allows adaptive browsing support for users with different level of experience, and a level of adaptability. The requirements analysis shows that the differences in the information needs of users with different levels of experience are not only quantitative, but qualitative. Experienced users are not only able to cope with a wider browsing space, but sometimes prefer to organize their search in a different way. That is why the user model and the interface of the system are designed to support a smooth transition in the access options provided to novice users and to expert users.

The Intelligent Helpdesk: Supporting Peer-Help in a University Course

Universities, experiencing growths in student enrollment and reductions in operating budgets, are faced with the problem of providing adequate help resources for students. Help resources are needed at an institution-wide and also at a course-specific level, due to the limited time of instructors to provide help and answer questions. The Intelligent IntraNet Peer Help Desk provides an integration and application of previously developed ARIES Lab tools for peer help to university teaching. One of its components, CPR, provides a subject-oriented discussion forum and FAQ-list providing students with electronic help. Another component, PHelpS, suggests an appropriate peer to provide human help. In both cases it is peer help, since the help originates from students themselves. The selection of the appropriate help resource (electronic or human) is based on modelling student knowledge and on a conceptual model of the subject material.

User Motivation and Persuasion Strategy for Peer-to-Peer Communities

In recent years, peer-to-peer systems have become more and more popular, especially with some successful applications like Napster and KaZaA. However, how to motivate user participation in peer-to-peer systems remains an open question for researchers. If few users are willing to participate in the community or make contributions to it, the peer-to-peer system will never become successful. To address the problem, this paper proposes a motivation strategy based on persuasion theories of social psychology. The main idea is to introduce a set of hierarchical memberships into p2p communities and reward active users with better quality of services. We have applied this strategy to a p2p system called Comtella and launched a study to test its effectiveness. The results of the study show that our motivation strategy is capable of stimulating the users to participate more actively and make more contributions to the community.