Privacy and Trust in Agent-Supported Distributed Learning

The objective of this chapter is to explore the challenges, issues, and solutions associated with satisfying requirements for privacy and trust in agent-supported distributed learning (ADL). Accordingly, the first section will present the background, context, and challenges. The second section will delve into the requirements for privacy and trust as seen in legislation and standards. The third section will look at available technologies for satisfying these requirements. The fourth section will discuss an often-ignored area—that of building trustworthy user interfaces for distributed-learning systems. Finally, the chapter will end with conclusions and suggestions for further research.

Intelligent Agents Supporting Distributed Collaborative Learning

In the context of distributed collaborative learning, it is usually difficult for students to be aware of others’ activities and for instructors to overview the process and regulate the collaboration. In order to facilitate collaborative learning, intelligent agents were developed to support the awareness and regulation of the collaboration. This chapter discusses the facilitation role of intelligent agents and how they support students and instructors in distributed collaborative-learning environments. By monitoring the collaboration, the agents compute statistics, detect possible problems, and give advice synchronously and asynchronously to the students and instructor based on their activities and requests. In so doing, the agents not only help students to self-regulate their activities but also help instructors to maintain an overview of the collaboration so that they can intervene when necessary.

A Multiagent Framework for an Adaptive E-Learning Systems

This chapter describes a multiagent system for delivering adaptive e-learning. This chapter also provides a discussion of three issues related to personalization in e-learning: technology advancement and the shift in perception of the learning process, one-size-fits-all versus personalized services, and the adaptation process. Finally, the chapter provides an overview of most known implemented systems for adaptive e-learning, as well as a detailed description of the architecture and components of the proposed multiagent framework.

Integrating Tutoring Systems for Distributed Learning Environments

This chapter discusses an integrated approach to designing and developing adaptive distributed learning environments. It presents a distributed learning environment based on agent technology and Web services technology. Agents are expected to be used as the core components in intelligent distributed learning environments because of their inherent natures: autonomous, intelligent, sociable, etc. However, to integrate agents into existing legacy learning environments or into heterogeneous learning environments, one may encounter many difficulties. They may be technical issues, economical issues, social issues, or even political issues. Web services technology, on the other hand, characterized by its standardized communication protocol, interoperability, and easy integration and deployment, is an excellent complimentary partner with agents in distributed learning environments. The integration of Web services and agents simplifies the complexity of development, saves time, and, most important of all, makes distributed learning environments feasible and practical. To take advantage of the merits of agents and Web services, we advocate agent-supported Web services in designing and developing distributed learning environments.

Intelligent Tutoring Systems for Distributed Learning

This chapter provides information on how to design intelligent tutoring systems for distributed learning to cater to individual learner needs and styles. It argues that intelligent tutoring systems must use the expertise that tutors use in a one-to-one teaching situation to build intelligent tutoring systems for distributed learning. Also, the appropriate psychological and educational theories must be used to build the domain module, student model, and pedagogical module. The components of intelligent tutoring systems are described, and the author makes the case that to build effective intelligent tutoring systems, a multidisciplinary team should be involved. Finally, the author identifies trends that are influencing the development of intelligent tutoring systems and suggests areas for future research and development.

A Human Collaborative Online Learning Environment Using Intelligent Agents

This chapter introduces the design and implementation of a multiagent system based on a collaborative online learning environment (COLE). The purpose of developing such an environment is to improve social competences along with traditional content-related ones in lifelong learning. As educators would be unable to handle the huge amount of data concerning human interactions in such a learning environment, a multiagent system approach is adopted. The concept of human collaboration and the ways that project-based learning (PBL) and portfolios can be used to improve social competences are discussed based on the Social Theory of Learning. The way that the System Analysis for Agent Systems (SAAS) method was used to identify services and agents is presented. A general review of multiagent system architectures is presented to justify the choice of an open system. The basis and architecture of the COLE are explained. In order to facilitate the implementation of particular agents, a generic agent (GAg) and its functionalities are presented.

A Language for Specifying Agent Systems in E-Learning Environments

In this chapter, we use the Chemical Reaction Metaphor (Banatre & Le Metayer, 1990, 1993, 1996) to model the interactions among program units, including the agents, clients, servers, and databases, in a multiagent-based e-learning system. Through case studies, we demonstrate that the Gamma language (Banatre & Le Metayer, 1990; Le Metayer, 1994) is suitable for specifying a multiagent system, particularly, because an agent’s properties, such as autonomy and mobility, can be captured concisely. The use of the high-level specification paves the way for solving architectural-design issues in building an e-learning environment. The Gamma specification of an agent system can be implemented in a hierarchical running environment, which is composed of nodes in different levels of a tree. Interactions among agents can be implemented in a unified mechanism for synchronization.

A VR-Based Virtual Agent System

Agent technology can be used to represent individuals participating in a virtual university. Avatars are virtual actors on behalf of students and instructors navigating in a three-dimensional (3D) virtual campus. This chapter presents a system based on virtual reality (VR) technology as well as agent technology that enables online discussions via different real-time communication channels. The system has a generic interface, which includes five scenes of a virtual university, as well as a set of plug-and-play communication agent tools. Each user is maintained by an intelligent agent that controls the navigation behavior based on a rule-based computation. Behaviors of each student are restricted and guided by intelligent agents. The system can be extended for the construction of any virtual university with 3D campus and online communication facilities.

Knowledge Management for Agent-Based Tutoring Systems

As the education field is becoming increasingly technology heavy, more educational systems involve line or interactive training and tutoring techniques, and lots of educational information becomes available via the intranet and World Wide Web. Managing large volumes of learning information and knowledge is one of the crucial issues for these educational systems, as appropriate knowledge management is the key to more effective and efficient learning. The chapter first discusses that an intelligent agent system could be successfully applied to the education field and then focuses on how knowledge management techniques play an important role in agent-based tutoring systems.

Intelligence in MAS-Based Distributed Learning Environments

This chapter first addresses the issue of the importance of intelligence in MAS-based DLEs. Then, it stresses that there are three main intelligent competencies in MAS-based DLEs: intelligent decision-making support, coordination and collaboration of the agents in MAS, and student modeling for personalization and adaptation in learning systems. It also describes in detail how to apply relevant AI techniques, including the introduction of AI techniques and their state-of-the-art application in the e-learning domain. Finally, future trends in the research and development of intelligence for MAS-based DLEs are discussed.