Educational Data Mining: Results from In Vivo Experiments to Teach - - PowerPoint PPT Presentation

educational data mining results from in vivo experiments
SMART_READER_LITE
LIVE PREVIEW

Educational Data Mining: Results from In Vivo Experiments to Teach - - PowerPoint PPT Presentation

Educational Data Mining: Results from In Vivo Experiments to Teach Different Physics Topics Advance Technology and Applied Science Research Center National Polytechnic Institute - Mexico Alejandro Ballesteros Romn Daniel Snchez Guzmn


slide-1
SLIDE 1

Educational Data Mining: Results from In Vivo Experiments to Teach Different Physics Topics

Daniel Sánchez Guzmán

Advance Technology and Applied Science Research Center National Polytechnic Institute - Mexico AAPT SM 2014, Minneapolis, MN

1

Alejandro Ballesteros Román

slide-2
SLIDE 2

Introduction

  • Educational Data Mining (EDM) uses different

algorithms for analyzing response and behavior in the teaching-learning process for obtaining useful patterns.

  • These algorithms let to analyze and classify

students' behavior or state of knowledge from different concepts.

2

slide-3
SLIDE 3

Introduction

  • Most of these algorithms have not been tested in

Physics Education Research.

  • This work presents the results obtained from

applying algorithms used by EDM for teaching different physics concepts applied to in-vivo experiments.

3

EDM Data sets* non-Physics Physics Total 67 27 94 71% 29% 100%

* Pittsburgh Science of Learning Center (PSLC - CMU). Data Shop Public Data Sets. https://pslcdatashop.web.cmu.edu/index.jsp?datasets=public

slide-4
SLIDE 4

How Educational Data Mining works?

4

slide-5
SLIDE 5

Implementation

  • EDM algorithms (Tree Decision Making, C4.5);

were applied with N = 395 students.

  • Level: High-school students.
  • Topic: Electric Circuits and Ohm’s Law.
  • Multiple choice questions: 6 (Academy design,
  • aprox. Electric Circuits Concept Evaluation - ECCE).

5

slide-6
SLIDE 6

Results

* Did not answer. Q3 Q6 Q5 Q4 Q2 Q1

6

slide-7
SLIDE 7

Results

* Did not answer. Q3 Q6 Q5 Q4 Q2 Q1

What does this mean?

7

slide-8
SLIDE 8

Results

* Did not answer. Q3 Q6 Q5 Q4 Q2 Q1

Most wrong answered question.

8

slide-9
SLIDE 9

Results

* Did not answer. Q3 Q6 Q5 Q4 Q2 Q1

Possibly: Confused or not attended concept during instruction. (C – Correct answer)

9

slide-10
SLIDE 10

Results

* Did not answer. Q3 Q6 Q5 Q4 Q2 Q1

Most correctly answered question.

10

slide-11
SLIDE 11

Results

* Did not answer. Q3 Q6 Q5 Q4 Q2 Q1

Possibly: Answer is inside the question or well- attended concept. (C – Correct answer)

11

slide-12
SLIDE 12

Results

* Did not answer. Q3 Q6 Q5 Q4 Q2 Q1

Most balanced question.

12

slide-13
SLIDE 13

Results

* Did not answer. Q3 Q6 Q5 Q4 Q2 Q1

Possibly: Well-defined question and well- attended concept. (B – Correct answer)

13

slide-14
SLIDE 14

Results

  • It is necessary to apply these algorithms with more

students for having a fine-grained results.

  • The use of valid inventories/test would eliminate

mistakes.

  • Patters obtained let us to identify mistakes and

wrong questions applied to students, also instruction could be highly improved.

14

slide-15
SLIDE 15

Questions? dsanchez@ipn.mx dsanchezgzm@gmail.com

15