Related Work

 < Day Day Up > 



Concerning agents in facilitating CSCL, several related works are worth noting.

Understanding Collaboration

In order to provide efficient and effective support to students in distributed collaborative-learning environments, many researchers choose to start by understanding the collaboration. Therefore, most efforts in facilitator agents such as IDLC (Okamoto et al., 1995), GRACILE (Ayala & Yano, 1996), and EPSILON (Soller, 2001) have been placed on designing intelligent modules that replace the instructor’s role in the collaboration. In order to obtain this goal, students are restricted to using “semistructured” interfaces such as menu-driven or sentence-openers to collaborate, which restrain the interaction channels and slow the communication process. Furthermore, the advice generated by these intelligent systems is based on its own understanding of the collaboration process, which has a high possibility of misinterpretation or misunderstanding. As a result, the advice might sometimes be inappropriate and confuse the students.

Intelligent Agents in Synchronous Collaborative- Learning Environment

Constantino-Conzalez and Suthers (2001) reported their research on coaching collaboration in a synchronous distance-learning environment with minimal reliance on the restricted communication devices such as sentence openers. They evaluated the potential contribution of tracking student participation and comparing students’ individual and group solutions. The coach has the ability to recognize relevant learning opportunities and to provide advice that encourages students to take these opportunities. They identified several advice types, such as discussion, participation, and feedback, from which the coach can choose. The experiment results showed that reasonable collaboration advice could be generated without the need for expert solutions or discourse under- standing. Our research is partially inspired by their work and aims at testing the role of agents in an asynchronous environment.

Instructor’s Role in Collaborative Learning

Dillenbourg (1999) claimed that the instructor retains a role in the success of collaborative learning. He further defines the “facilitator” role of an instructor as not to provide the right answer or to say which group member is right, but to perform a minimal pedagogical intervention (e.g., provide some hint) in order to redirect the group work in a productive direction or to monitor which members are left out of the interaction. He identified three main categories of agents in a CSCL environment (Dillenbourg et al., 1997): subagents, co-agents and superagents. The facilitator agents presented in this chapter fit in the superagents category.

Plug-In Agents in Learning Environments

Ritter and Koedinger (1996) attempted to build learning environments that incorporate tutoring agents into pre-existing software packages. The tutor agent is designed to be general so that it can be integrated to a wide range of complex tools. To achieve this goal, a translator is designed to transfer the tool- specific information into the internal representation of the tutor agent. With the help of the translator, tools in different domains are able to share the same tutor agent. The facilitator agents we present are designed with a similar idea in mind.



 < Day Day Up > 



Designing Distributed Environments with Intelligent Software Agents
Designing Distributed Learning Environments with Intelligent Software Agents
ISBN: 1591405009
EAN: 2147483647
Year: 2003
Pages: 121

flylib.com © 2008-2017.
If you may any questions please contact us: flylib@qtcs.net