The Open UniversitySkip to content
 

GAOOLE: a Gaia Design of Agent-Based Online Collaborative Learning Environment

Liu, Shuangyan; Joy, Mike and Griffiths, Nathan (2009). GAOOLE: a Gaia Design of Agent-Based Online Collaborative Learning Environment. In: Proceedings of the 8th European Conference on e-Learning, Academic Conferences and Publishing International, pp. 339–350.

Full text available as:
[img]
Preview
PDF (Accepted Manuscript) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (523kB) | Preview
URL: http://academic-conferences.org/ecel/ecel2009/ecel...
Google Scholar: Look up in Google Scholar

Abstract

An intelligent collaborative learning environment (iCLE) provides an online learning community with an interactive and multi-functional work area with intelligent support for the whole cycle of collaborative education, including organizing teams, advising on group work and communication, tutoring, and testing individual contributions. An agent based approach lends itself to developing iCLE systems since many of the desired properties and requirements of iCLE systems coincide with those provided by the use of agents, such as autonomy, reactiveness and proactiveness (goal-oriented). Existing agent-based designs for online collaborative learning identify the agent types and the system topology, but lack certain design specifications. In particular, there is a lack of precision with respect to areas such including: the key roles that intelligent agents can play in online collaborative learning management; the computational resources consumed and generated by a role for performing a pedagogical task; the protocols adopted for the interactions between different roles; the agent types with mapped roles and the number of instances of each type in an actual system; and the services that the agents provide. Fully specifying these aspects will enable the system to fully exploit the strengths of agents (including pro-activeness, autonomy and flexibility). In this paper, we propose a new design, GAOOLE (Gaia Design of Agent-based Online Collaborative Learning Environment), which includes a detailed analysis and design specification. It consists of five sub-models: the environment model (describing the computational resources in a collaborative learning environment that are needed by the identified roles and their relationships with them), the roles model (describing the attributes of the roles for managing online collaborative learning – responsibilities, permissions, activities and protocols), the interaction model (defining the protocols for each type of inter-role interaction), the agent model (defining the types of agents and the number of instances of each agent type in actual system) and the services model (describing the services associated with each agent type). We specify these models in this paper by following the Gaia methodology. By applying an established agent-oriented methodology we develop a detailed system design that makes full use of the agent-based approach both in terms of system development, for example by facilitating use of existing components and systems, and in system use, providing characteristics such as flexibility and pro-activeness. In this paper we give an overview of the design, and focus in particular on how the collaborative aspects of the learning environment are supported.

Item Type: Conference or Workshop Item
Copyright Holders: 2009 The Authors
ISBN: 1-906638-52-7, 978-1-906638-52-8
Keywords: intelligent collaborative learning environment; educational agent; design of agent-based systems; gaia methodology; system integration
Academic Unit/School: Faculty of Science, Technology, Engineering and Mathematics (STEM) > Knowledge Media Institute (KMi)
Faculty of Science, Technology, Engineering and Mathematics (STEM)
Item ID: 42144
Depositing User: Shuangyan Liu
Date Deposited: 11 Mar 2015 14:50
Last Modified: 05 Oct 2016 00:16
URI: http://oro.open.ac.uk/id/eprint/42144
Share this page:

Download history for this item

These details should be considered as only a guide to the number of downloads performed manually. Algorithmic methods have been applied in an attempt to remove automated downloads from the displayed statistics but no guarantee can be made as to the accuracy of the figures.

Actions (login may be required)

Policies | Disclaimer

© The Open University   + 44 (0)870 333 4340   general-enquiries@open.ac.uk