SLIDE 1
ET-805 Open Learner Models
Ramkumar.Rajendran@iitb.ac.in
From Last Class
- Cohen’s Kappa
Muddy Points Multi-class classifier
2
ET-805 Open Learner Models Ramkumar.Rajendran@iitb.ac.in From Last - - PowerPoint PPT Presentation
ET-805 Open Learner Models Ramkumar.Rajendran@iitb.ac.in From Last - - PowerPoint PPT Presentation
ET-805 Open Learner Models Ramkumar.Rajendran@iitb.ac.in From Last Class - Cohens Kappa Muddy Points Multi-class classifier 2 Activity - Discussion What is the difference between F1 score and Kappa? 23 7 6 44 Precision = 23/30
SLIDE 2
SLIDE 3
Activity - Discussion
What is the difference between F1 score and Kappa? Precision = 23/30 Recall = 23/29 F1 Score = 2/ (30/23 + 29/23) = 46/59 = 0.77 = a,b = 2/ (1/a + 1/b) Kappa = 0.65 (0.8375 - 0.53)/ 0.47
3
23 7 6 44
SLIDE 4
Activity - Every One say one
What is the purpose of learner model in ITS? LM visible to the learners?
- To adapt the content ( to use the data from LM in ped)
- Model the learner
- LM are not visible?
4
SLIDE 5
Open Learner Models
- Open learner models allow the learner (and/or others) to view
information about him/herself
5
Bull, Susan, and Judy Kay. "Open learner models." In Advances in intelligent tutoring systems, pp. 301-322. Springer, Berlin, Heidelberg, 2010. Bull, Susan, and Judy Kay. "Metacognition and open learner models." In The 3rd workshop on meta-cognition and self-regulated learning in educational technologies, at ITS2008, pp. 7-20. 2008. Bull, Susan, and Judy Kay. "Open learner models as drivers for metacognitive processes." In International handbook of metacognition and learning technologies, pp. 349-365. Springer, New York, NY, 2013.
SLIDE 6
Activity - TPS
Think: What is the benefit/reason for OLM. Write two points (3 minutes) Pair: Copy your peer’s answers. Together arrange the reason for OLM in the order of importance (3 minutes) Share
6
SLIDE 7
Activity - Class Response
- OLM motivates the student to complete the task
- Learner can compare with the peers/average score of the class
- Reflect
- Change their cognitive strategies
7
SLIDE 8
Open Learner Models
- Improves the accuracy of the learner model
- Assists to plan or monitor
- Right of learners to view their data
- Compare their performance against domain or peers
8
SLIDE 9
Activity - Every One say one
What are the drawbacks of Open Learner Model?
- Student might dropout of the course
- Privacy
- Learner can learn how to game the system
- Demotivating
- 9
SLIDE 10
Open Learner Model
- How much information to learner?
- Only performance!
- How to represent?
- Text, skill meters…
- Permission to the model
- Can they edit, add information, share with peers, etc.
10
SLIDE 11
SQL Tutor
11
SLIDE 12
Impact of OLM in SQL Tutor
- No significant difference in post-test score
- However, Significant learning gains for less able students
compared to control group
- More able students showed more self-confidence
12
Mitrovic, A. & Martin, B. Evaluating the Effect of Open Student Models on Self-Assessment International Journal of Artificial Intelligence in Education 17(2) (2007), 121-144.
SLIDE 13
Open Learner Models Examples
13
Dr Susan Bull (Principal Author), Dr Steven Quigley & Mr Andrew Mabbott (2006) Computer-based formative assessment to promote reflection and learner autonomy, Engineering Education, 1:1, 8-18
SLIDE 14
OLM
14
SLIDE 15
Activity - Second Assignment
Ped Logic: When the learner not able to answer the questions in the first attempt, give them example problems. 2: Demonstrates how to solve the problem 3: Ask questions about prior knowledge, difficulties etc Domain Model: Three laws, figure and equation. Example problem, Assessment question, simulation/video for demo, hints, feedback, Learner Model:
15
SLIDE 16
Before Next Class
- Try CTAT, ASTUS and ASSISTMENT
- We will compare these three authoring tools in next class
- Do it before attending next class
16
SLIDE 17
Last Activity - Muddy Points
List down
- two important and
- two least clear
(muddy) points from today’s class
- https://tinyurl.com/et8
05mp
17