Using Data-Driven Discovery Techniques for the Design and Improvement of Educational Systems

John StamperPittsburgh Science of Learning CenterHuman-Computer Interaction InstituteCarnegie Mellon University

4/8/2013

The Classroom of the Future

Which picture represents the “Classroom of the Future”?

2

3

The Classroom of the Future

The answer is both!Depends of how much money you have...

… but maybe not what you think…

4

The Classroom of the FutureRich vs. Poor– Poor kids will be forced to rely on “cheap” technology– Rich kids will have access to “expensive” teachers

We are seeing this today!– Waldorf school in Silicon Valley – no technology– NGLC Wave III Grants– MOOCs – Growth of adaptive technology companies– Online instruction– … and more…

5

What does this mean?

My view is that we cannot stop this, I believe we must accept that economics will force this route.

We should focus on improving learning technology• New ways to improve teacher-student access• Add more adaptive features to learning software

Adaptive learning, at scale, using data!

6

Educational Data Mining

• “Educational Data Mining is an emerging discipline, concerned with developing methods for exploring the unique types of data that come from educational settings, and using those methods to better understand students, and the settings which they learn in.” – www.educationaldatamining.org

7

Types of EDM methods(Baker & Yacef, 2009)

• Prediction– Classification– Regression– Density estimation

• Clustering• Relationship mining

– Association rule mining– Correlation mining– Sequential pattern mining– Causal data mining

• Distillation of data for human judgment• Discovery with models

Emerging Communities

• Society for Learning Analytics Research– First conference: LAK2011

• International Educational Data Mining Society– First conference: EDM2008– Publishing JEDM since 2009

• Plus an emerging number of great people working in this area who are (not yet) closely affiliated with either community

Emerging Communities

• Joint goal of exploring the “big data” now available on learners and learning

• To promote– New scientific discoveries & to advance learning sciences– Better assessment of learners along multiple dimensions

• Social, cognitive, emotional, meta-cognitive, etc.• Individual, group, institutional, etc.

– Better real-time support for learners

10

EDM Methods to discuss

• Prediction – understand what the student knows

• Discovery with models – improve understanding of the structure of knowledge

11

LearnLabPittsburgh Science of Learning Center (PSLC)• Created to bridge the Chasm between science &

practice– Low success rate (<10%) of randomized field trials

• LearnLab = a socio-technical bridge between lab psychology & schools– E-science of learning & education – Social processes for research-practice engagement

• Purpose: Leverage cognitive theory and computational modeling to identify the conditions that cause robust student learning

Chemistry Virtual Lab

Algebra Cognitive Tutor

Ed tech + wide use = Research in practice

=

LearnLab: Data-driven improvement infrastructure

• 2004-14, ~$50 million• Tech enhanced courses,

assessment, & research• School cooperation• In vivo experiments

+

English Grammar Tutor

Educational Games

Interaction data is surprisingly revealing

• Accurate assessment during learning

• Detect student work ethic, engagement …

• Discover better models of what is hard to learn

R = .82

Online interactions => state tests

Learning Curve Analysis

Flat curve => improvement opportunity

• Central Repository– Secure place to store & access research data– Supports various kinds of research

• Primary analysis of study data• Exploratory analysis of course data• Secondary analysis of any data set

• Analysis & Reporting Tools– Focus on student-tutor interaction data– Data Export

• Tab delimited tables you can open with your favorite spreadsheet program or statistical package

• Web services for direct access

DataShop

1414

Repository

• Allows for full data management• Controlled access for collaboration• File attachments• Paper attachments• Great for secondary analyses

How big is DataShop?

15

How big is DataShop?Domain Files Papers Datasets Student Actions Students Student Hours

Language 64 11 78 6,237,523 6,499 6,877 Math 222 53 189 75,754,530 37,218 173,175Science 92 19 93 13,849,756 16,939 45,465Other 18 12 50 8,604,016 13,018 31,111

Total396 95 410 104,445,825 73,674 256,630

As of April 2013

16

What kinds of data?• By domain based on studies from the Learn Labs

• Data from intelligent tutors

• Data from online instruction

• Data from games

The data is fine grained at a transaction level!

17

Web Application

• Explore data through the DataShop tools• Where is DataShop?

– http://pslcdatashop.org– Linked from DataShop homepage and learnlab.org

• http://pslcdatashop.web.cmu.edu/about/• http://learnlab.org/technologies/datashop/index.php

Getting to DataShop

1919

• KC: Knowledge component– also known as a skill/concept/fact– a piece of information that can be used to

accomplish tasks– tagged at the step level

• KC Model:– also known as a cognitive model or skill model– a mapping between problem steps and knowledge

components

DataShop Terminology

20

Getting the KC Model Right!

The KC model drives instruction in adaptive learning– Problem and topic sequence– Instructional messages– Tracking student knowledge

21

What makes a good KC Model?

• A correct expert model is one that is consistent with student behavior.

• Predicts task difficulty • Predicts transfer between instruction and test

The model should fit the data!

22

Good KC Model => Good Learning Curve

• An empirical basis for determining when a cognitive model is good

• Accurate predictions of student task performance & learning transfer– Repeated practice on tasks involving the same skill

should reduce the error rate on those tasks=> A declining learning curve should emerge

23

A Good Learning Curve

24

How do we make KC Models?

25

Traditionally CTA has been used

But Cognitive Task Analysis has some issues…– Extremely human driven – It is highly subjective– Leading to differing results from different analysts

And these human discovered models are usually wrong!

26

If Human centered CTA is not the answer

How should these models be designed?

They shouldn’t!

The models should be discovered not designed!

27

Solution– We have lots of log data from tutors and other systems

– We can harness this data to validate and improve existing student models

28

29

Human-Machine Student Model DiscoveryDataShop provides easy interface to add and modify

KC models and ranks the models using AFM

29

Human-Machine Student Model Discovery

3 strategies for discovering improvements to the student model

– Smooth learning curves

– No apparent learning

– Problems with unexpected error rates

30

A good cognitive model produces a learning

curve

Without decomposition, using just a single “Geometry” skill,

Is this the correct or “best” cognitive model?

no smooth learning curve.

a smooth learning curve.

But with decomposition, 12 skills for area,

(Rise in error rate because poorer students get assigned more problems)

Inspect curves for individual knowledge components (KCs)

Some do not =>Opportunity to improve model!

Many curves show a reasonable decline

32

No apparent Learning

33

Problems with Unexpected Error Rates

34

Inspect problems to hypothesize new KC labels

• Here scaffolding is originally absent, but other problems have fixed scaffolding– They start with columns for square & area

These strategies suggest an improvement

– Hypothesized there were additional skills involved in some of the compose by addition problems

– A new student model (better BIC value) suggests the splitting the skill.

36

Redesign based on Discovered Model

Our discovery suggested changes needed to be made to the tutor

– Resequencing – put problems requiring fewer skills first

– Knowledge Tracing – adding new skills– Creating new tasks – new problems– Changing instructional messages, feedback or

hints

37

Study : Current tutor is control

• Current fielded tutor only uses scaffolded problems

Study: Treatment

• Scaffolded, given areas, plan-only, & unscaffolded

• Isolate practice on problem decomposition

Study Results

• Much more efficient & better learning on targeted decomposition skills

Post-test % correct by item type

Control: Original tutor

Treatment: Model-based

redesign

0.7

0.75

0.8

0.85

0.9

0.95

1

CompositionArea

Instructional time (minutes) by step type

Control: Original tutor

Treatment: Model-based

redesign

0

10

20

30 Composition steps Area and other steps

Design

DeployData

Discover

Translational Research Feedback Loop

Can a data-driven process be automated & brought to scale?

Yes!

• Combine Cognitive Science, Psychometrics, Machine Learning …

• Collect a rich body of data• Develop new model discovery algorithms,

visualizations, & on-line collaboration support

42

DataShop’s “leaderboard” ranks discovered cognitive models100s of datasets coming from ed tech in math, science, & language

Some models are machine generated (based on human-generated learning factors)

Some models are human generated

43

Metrics for model prediction

• AIC & BIC penalize for more parameters, fast & consistent

• 10 fold cross validation• Minimize root mean squared error (RMSE) on

unseen data

44

Automated search for better models

Learning Factors Analysis (LFA) (Cen, Koedinger, & Junker, 2006) • Method for discovering & evaluating cognitive models• Finds model “Q matrix” that best predicts student learning data• Inputs

Data: Student success on tasks over time Factors hypothesized to explain learning

• Outputs Rank order of most predictive Q matrix Parameter estimates for each

Simple search process example: modifying Q matrix by input factor to

get new Q’ matrix

• Produces new Q matrix• Two new KCs (Sub-Pos & Sub-Neg) replace old KC (Sub)

• Redo opportunity counts

• Q matrix factor Sub split by factor Neg-result

OriginalModel

BIC = 4328

4301 4312

4320

43204322

Split by Embed Split by Backward Split by Initial

43134322

4248

50+

4322 43244325

15 expansions later

LFA: Best First Search Process

Cen, H., Koedinger, K., Junker, B. (2006).  Learning Factors Analysis: A general method for cognitive model evaluation and improvement. 8th International Conference on Intelligent Tutoring Systems.

• Search algorithm guided by a heuristic: AIC

• Start with single skill cog model (Q matrix)

Scientist “crowd”sourcing: Feature input comes “for free”

Scientist generated models

48

Union of all hypothesized KCs in human generated models

Validating Learning Factors Analysis

• Discovers better cognitive models in 11 of 11 datasets …

Koedinger, McLaughlin, & Stamper (2012). Automated student model improvement. In Proceedings of the Fifth International Conference on Educational Data Mining. [Conference best paper.]

Data from a variety of educational technologies & domains

50

Numberline Game

Statistics Online Course English Article Tutor

Algebra Cognitive Tutor

Applying LFA across domains

11 of 11 improvedmodels

9 of 11 equal or greater learning

Variety of domains& technologies

Can we go even bigger?

52

Competitions?

KDD Cup CompetitionKnowledge Discovery and Data Mining (KDD) is the most

prestigious conference in the data mining and machine learning fields

KDD Cup is the premier data mining challenge

2010 KDD Cup called “Educational Data Mining Challenge”

Ran from April 2010 through June 2010

54

KDD Cup CompetitionCompetition goal is to predict student responses given tutor data

provided by Carnegie Learning

Dataset Students Steps File sizeAlgebra I 2008-2009 3,310 9,426,966 3 GBBridge to Algebra 2008-2009

6,043 20,768,884 5.43 GB

55

KDD Cup Competition 655 registered participants

130 participants who submitted predictions

3,400 submissions

KDD Cup Competition Advances in prediction, cognitive modeling, new methods

applied to EDM

Spawned a number of workshops and papers

The datasets are now in the “wild” and showing up in non KDD conferences

New competitions to continue momentum

57

Marigames.org

• Two stage competition with $100,000 in prizes– $50,000 Game Development– $50,000 Educational Data Mining

• Goal is to go beyond individual datasets• This requires common data formats

58

Take aways

• The amount of data coming from educational technology is growing exponentially

• Huge potential for EDM to improve educational systems • Optimal instructional design requires discoveries (The

student is not like me)

• These methods require common forms of data for analysis (standards!)

59

Opportunities

• New Learning Science and Engineering professional masters degree at Carnegie Mellon University

• New concentration in Learning Analytics, MA in Cognitive Studies in Education at Teachers College, Columbia University

• Other programs in the works

60

Thank you

Special Thanks to:Ken Koedinger, Director LearnLab Ryan Baker, President IEDMSSteve Ritter, Carnegie Learning

61

62

http://pslcdatashop.orgQuestions?

john@stamper.orghttp://dev.stamper.org