21st International Joint Conference on Artificial Intelligence (IJCAI), Pasadena

Intelligent Tutoring Systems: New Challenges and Directions

author: Cristina Conati, Department of Computer Science, University of British Columbia
introducer: Luigia Carlucci Aiello, Department of Computer and Systems Sciences, Sapienza University of Rome
published: July 22, 2009, recorded: July 2009, views: 1606

Slides

Slides
0:00	Intelligent Tutoring Systems: New Challenges and Directions
3:17	Preamble (1)
4:08	Preamble (2)
4:38	Intelligent Tutoring Systems - ITS (1)
5:12	Background and definitions
5:34	Precursors of ITS (1)
6:00	Precursors of ITS (2)
7:10	CAI systems (cont.)
8:58	Good Human Tutors
9:41	Intelligent Tutoring Systems - ITS (2)
10:27	Ideal ITS
13:17	Achievements
14:14	How much learning improvement?
14:49	However…
15:11	Coached problem solving
15:47	Beyond Coached Problem Solving
16:01	Key Trends in ITS (1)
17:33	Challenges
18:42	Key Trends in ITS (2)
19:15	Our Approach
19:55	Achievements and Trends
20:07	Key Trends in ITS (3)
20:19	Adaptive Support for Analogical Problem solving
20:23	Sample Physics Example
20:30	Adaptive Support for Analogical Problem solving
20:52	Relevant Meta-Cognitive Skills
22:38	Impact of Student Characteristics
23:32	Impact of Problem/Example Similarity
24:49	Adaptive support for Example Studying
25:24	- Demo
26:36	EA-Coach Architecture
28:44	Decision Theoretic Approach to Example Selection
29:57	Evaluation
30:42	Results
31:36	Discussion
32:23	Eye Tracking and Self-explanation
32:51	Sample Activity (1)
33:16	User Model
34:50	Sample Activity (2)
35:02	User Model
35:04	Results on Accuracy
36:04	Discussion
36:15	Key Trends in ITS (4)
37:07	Educational Games
38:12	Example: The Prime Climb Educational Game
39:36	Our Solution
40:06	Initial Prime Climb Pedagogical Agent
40:46	Hints at Incremental Level of Detail
41:01	What else do we need?
41:57	Long Term Goal
42:27	How to Assess Emotions?
43:05	But Things are not Always that Easy
43:42	Challenge
44:23	Previous Approaches
45:23	Our solution
45:49	The Prime Climb Affective Model (1)
46:33	OCC Theory
48:01	The Predictive Part of the Model
49:21	Adding Diagnostic Information
49:32	Diagnostic Assessment
50:40	The Prime Climb Affective Model (2)
50:56	EMG signal
51:09	The Prime Climb Affective Model (2)
51:30	Evaluation
52:05	Evaluation - Diagram
52:18	Emotional Reports
52:37	Evaluation - Diagram
53:40	Lots of Exciting Future Work
54:47	Conclusions
56:22	Thanks to…
56:48	- Questions

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

Lecture popularity: You need to login to cast your vote.

Description

Can we devise educational systems that provide individualized instruction tailored to the needs of the individual learners, as many good teachers do? Intelligent Tutoring Systems is the interdisciplinary field that investigates this question by integrating research in Artificial Intelligence, Cognitive Science and Education. Successful intelligent tutoring systems have been deployed to support traditional problem solving activities by tailoring the instruction to the student's domain knowledge. In this talk, I will present a variety of projects that illustrate our efforts to extend the scope of intelligent tutors to both support novel forms of pedagogical interactions (e.g., example-based and exploration-based learning) and adapt to student's traits beyond knowledge (e.g., student's meta-cognitive abilities and affective states). I will discuss the challenges of this research, the results that we have achieved so far and future opportunities.