1
1) Empirical-Based, Evolutionary
Design of FLE/Agents
•
•
•
•
•
Background
Knowledge building environments
Method
Empirical study and design
Pedagogical agent system
A. Mørch, 30.03.2006, 2.1
2
DoCTA NSS project
• Design and use Of Collaborative
Telelearning Artefacts – Natural
Science Studios
• Goal: Study social, cultural and
pedagogical aspects of shared artefacts in
distributed collaborative learning and apply
the findings to the design of new learning
environments
A. Mørch, 30.03.2006, 2.1
3
Knowledge building
• A model for collaborative learning (Scardemalia
& Bereiter, 1994)
• Students learn and interact by “talking”
(reasoning aloud) with peers to develop
explanations of scientific phenomena
• Formulate research questions, answering
them independently, and finding arguments
• Computer supported knowledge building
environments:
– CSILE, Knowledge Forum
– FLE
A. Mørch, 30.03.2006, 2.1
4
Method
• Empirical-based design
– Identify need for improved knowledge
building based environment based on
data from using an existing system
• Evolutionary design
– Identify ways to integrate software agents
with existing system
A. Mørch, 30.03.2006, 2.1
5
Empirical study
• Two secondary school classes in Norway
(9th grade)
• 3 week pilot; 4 week field trial (2001, 2002)
• Collaborative learning in small groups
• Discussing science problems
• Knowledge domain: Ethical aspects of
biotechnology
• Computer supported environment without
software agents (FLE system)
A. Mørch, 30.03.2006, 2.1
6
FLE (Future Learning Environment)
• Developed at Media Lab, University of Art
and Design Helsinki (http://fle3.uiah.fi/)
• Open-source groupware implemented in the
Python language using SOAP platform
• Designed based on pedagogical and
psychological research in networked
learning and knowledge building at
University of Toronto and University of
Helsinki (Hakkarainen, Lipponen & Järvelä, 2002)
A. Mørch, 30.03.2006, 2.1
7
FLE interface
Viewing mode (threaded list of
previous postings)
Writing/reply mode
(editor with message
categories)
A. Mørch, 30.03.2006, 2.1
8
FLE message categories
• Categories of progressive inquiry:
–
–
–
–
–
Problem
My working theory
Deepening knowledge
Summary
Meta-comment
A. Mørch, 30.03.2006, 2.1
9
Physical setting in one of the
schools
A. Mørch, 30.03.2006, 2.1
10
Method
•
•
•
•
•
Observation
Video recording
Data logging
Interviews
Interaction analysis
A. Mørch, 30.03.2006, 2.1
11
Data excerpts: Interview
When asked about the usefulness of the FLE categories,
a student said:
“It was kind of smart! Because you can see what it [the message] is about.
That’s reliable knowledge and that’s a summary [pointing to two KB notes on
the screen]. You know immediately what it is.”
However, when later asked to demonstrate his
understanding of the difference between “My Working
Theory” note (MWT) and a “Summary” note he says
(modifies his initial misunderstanding of two categories):
“… if we had sent this to them [pointing to a note he has labeled
MWT] and you ask what it is supposed to mean - is it a working
theory or is it a summary, right? But you see it first by its small
[category abbreviation] … oh -it is a summary after all, okay!”
A. Mørch, 30.03.2006, 2.1
12
Summary of findings
• Students had difficulties choosing
knowledge building categories
• Instructors had difficulties following the
distributed collaboration process and
guiding the students
• Tentative conclusion: Need to find
alternative ways of facilitating distributed
knowledge building
A. Mørch, 30.03.2006, 2.1
13
Design implications
• Software agents can be useful as
scaffold in semi-structured knowledge
domains
• Pedagogical agents
• Agent system features
A. Mørch, 30.03.2006, 2.1
14
Pedagogical agents
• “Pedagogical agents can be
autonomous and/or interface agents
that support human learning in the
context of an interactive learning
environment.”
– Johnson, et al. (2000)
A. Mørch, 30.03.2006, 2.1
15
Agent system features
• Agent as an observer
– Collect information
• Participant, activity, timestamp
• Last log on, last contribution (for each participant)
– Compute statistics
• Agent as an advisor
– Present statistics
– Encourage non-active students to be more
active
– Advice students on the use of knowledgebuilding categories
A. Mørch, 30.03.2006, 2.1
16
System architecture
FLE3
Knowledge
Building
Admin
Chat
WebTop
User Interface
Assistant GUI
Observation:
Student activities
Instructor activities
Advice
Generation
Updates &
Who-is-online
Statistic
Generation
DB:log
KB:rules
Advice feature analysis:
Assistant
A. Mørch, 30.03.2006, 2.1
Message feature
Student feature
Instructor activity
Confidence factor
Learning
CN2
17
Technical detail
• Languages
– Python (Fle3) and Java (agent applet
interface)
• Database
– MySQL
• Learning algorithm
– CN2 (Clark & Niblett, 1989)
• Knowledge representation
– RuleML
A. Mørch, 30.03.2006, 2.1
18
Student Assistant Agent
A. Mørch, 30.03.2006, 2.1
19
Instructor Assistant Agent
A. Mørch, 30.03.2006, 2.1
20
References
•
•
•
•
Jondahl, S. and Mørch, A. (2001). Simulating Pedagogical
Agents in a Virtual Learning Environment, Proceedings IRIS24, pp. 15-28.
Chen, W. and Wasson, B. (2002) An Instructional Assistant
Agent for Distributed Collaborative Learning. Proceedings ITS2002, pp. 609-618
Dolonen, J., Chen, W. and Mørch, A. (2003). Integrating
Software Agents with FLE3. Proceedings of CSCL 2003,
Bergen, Norway. Kluwer Academic Publishers, pp. 157-161.
Mørch A, Dolonen J, Omdahl K. (2003). Integrating Agents
with an Open Source Learning Environment. Proceedings of
International Conference on Computers in Education 2003
(ICCE 2003), Dec. 2-5, Hong Kong: AACE Press, 393-401.
A. Mørch, 30.03.2006, 2.1