Using Bayesian Networks to Predict Test Scores

Slides:



Advertisements
Similar presentations
Mastery Learning is a style of assessment in which the student must demonstrate mastery of the assignment by correctly answering a certain number of problems.
Advertisements

Level 1 Recall Recall of a fact, information, or procedure. Level 2 Skill/Concept Use information or conceptual knowledge, two or more steps, etc. Level.
Welcome to Coordinate Algebra!!!
Regression Analysis Module 3. Regression Regression is the attempt to explain the variation in a dependent variable using the variation in independent.
Modeling Student Knowledge Using Bayesian Networks to Predict Student Performance By Zach Pardos, Neil Heffernan, Brigham Anderson and Cristina Heffernan.
December 14, 2010 Proportionality Through Similarity and Geometry.
Effective Skill Assessment Using Expectation Maximization in a Multi Network Temporal Bayesian Network By Zach Pardos, Advisors: Neil Heffernan, Carolina.
Data Mining CS 341, Spring 2007 Lecture 4: Data Mining Techniques (I)
Using Mixed-Effects Modeling to Compare Different Grain-Sized Skill Models Mingyu Feng, Worcester Polytechnic Institute Neil T. Heffernan, Worcester Polytechnic.
IBM Proof of Technology Discovering the Value of SOA with WebSphere Process Integration © 2005 IBM Corporation SOA on your terms and our expertise WebSphere.
Determining the Significance of Item Order In Randomized Problem Sets Zachary A. Pardos, Neil T. Heffernan Worcester Polytechnic Institute Department of.
PSAT. WHAT IS THE PSAT  PSAT/NMSQT stands for Preliminary SAT/ National Merit Scholarship Qualifying Test  Students take the PSAT to:  Prepare for.
Compare, Represent, and Evaluate Functions ABLE Teacher Academy.
Mathematical Processes GLE  I can recognize which symbol correlates with the correct term.  I can recall the correct definition for each mathematical.
An innovative learning model for computation in first year mathematics Birgit Loch Department of Mathematics and Computing, USQ Elliot Tonkes CS Energy,
Midterm Review Rao Vemuri 16 Oct Posing a Machine Learning Problem Experience Table – Each row is an instance – Each column is an attribute/feature.
Extended Assessments Elementary Mathematics Oregon Department of Education and Behavioral Research and Teaching January 2007.
Least-Squares Regression Section 3.3. Why Create a Model? There are two reasons to create a mathematical model for a set of bivariate data. To predict.
Statistics for the Social Sciences Psychology 340 Fall 2013 Correlation and Regression.
Basic Concepts of Correlation. Definition A correlation exists between two variables when the values of one are somehow associated with the values of.
Math Sunshine State Standards Wall poster. MAA Associates verbal names, written word names, and standard numerals with integers, rational numbers,
Math Leadership Support Network ’09-’10 Mathematics Leadership Support Network Presentation Provided Jointly by the P-12 Math and Science Outreach Division.
Expressions in Geometry.  Today’s standard: CCSS.MATH.CONTENT.7.EE.B.4  Use variables to represent quantities in a real-world or mathematical problem,
CSE 5331/7331 F'07© Prentice Hall1 CSE 5331/7331 Fall 2007 Machine Learning Margaret H. Dunham Department of Computer Science and Engineering Southern.
Assessment embedded in step- based tutors (SBTs) CPI 494 Feb 12, 2009 Kurt VanLehn ASU.
11/30 Warm Up- Monday Calculator Skills: 1.I can use y= when I see an __________ sign and one type of __________. 2.I can use STAT ENTER when I have two.
Welcome to Altadena Middle School! School! Key Points for Curriculum Night Curriculum Goals Homework Expectations Attendance and Assignments Late/Missing.
Mathematics Enrichment Program 11/9 08 – 11/30/08.
General Education Assessment Report Assessment Cycle.
Slide Slide 1 Chapter 10 Correlation and Regression 10-1 Overview 10-2 Correlation 10-3 Regression 10-4 Variation and Prediction Intervals 10-5 Multiple.
Math Test Overview The Mathematics Test is divided into two equally weighted parts: On Part I - 25 questions; 45 minutes; Casio fx-260 On Part II - 25.
Characteristics of HSAP Standards based Standards based 62 Multiple Choice items (1 point each for a total of 62 points) 62 Multiple Choice items (1 point.
Week 2 Normal Distributions, Scatter Plots, Regression and Random.
MATH BY MEAGHAN, ROWEN, ELSIE. CONTENT LIST ▪ INTRODUCTION : Past vs Present ▪ SELECTING APPROPRIATE MATH : Math Standards ▪ RESEARCH ON MATH INSTRUCTION.
DESCRIPTION OF THE ACT TEST There will always be 60 questions to be completed in 60 minutes. Questions address content through pre-calculus.
Data-Driven Education
Brief Intro to Machine Learning CS539
Year 9 Mathematics Algebra and Sequences
Core Methods in Educational Data Mining
ALGEBRA PATTERNS & ALGEBRAIC THINKING
Strategies That Support Differentiated Processing
Chapter 7. Classification and Prediction
How to interact with the system?
PSSA Parent University
PD Monday March 14, 2016.
Strategies That Support Differentiated Processing
METHOD TEST PREP EDUCATIONAL SERIES
Data Mining Lecture 11.
8th Grade Mathematics Curriculum
Towards building a better cognitive model
Mingyu Feng Neil Heffernan Joseph Beck
Gerd Kortemeyer, William F. Punch
CHAPTER 26: Inference for Regression
Introduction to Systems Analysis and Design
Detecting the Learning Value of Items In a Randomized Problem Set
Chapter 10 Correlation and Regression
CS539: Project 3 Zach Pardos.
Predicting Student Performance: An Application of Data Mining Methods with an Educational Web-based System FIE 2003, Boulder, Nov 2003 Behrouz Minaei-Bidgoli,
Behrouz Minaei, William Punch
Addressing the Assessing Challenge with the ASSISTment System
The Behavior of Tutoring Systems
Neil T. Heffernan, Joseph E. Beck & Kenneth R. Koedinger
How to interact with the system?
Warm-up New Seats.
Random Rectangles When given the cue turn the paper over. Within 5 seconds make a guess for the average area of the rectangles. When given the cue turn.
Mike Timms and Cathleen Kennedy University of California, Berkeley
Core Methods in Educational Data Mining
Claim 1: Concepts and Procedures
Mastery Assessment in Teaching Statistics
Presentation transcript:

Using Bayesian Networks to Predict Test Scores by Zach Pardos Neil Heffernan, Advisor 11/9/2018 ASSISTment

Introduction Overview ASSISTment tutoring system The Task Bayesian networks Platform selection 11/9/2018 ASSISTment

ASSISTment Tutoring System Online tutoring system developed at WPI - Assess student knowledge/learning Assists and prepares students for the MCAS 2nd year of operation Participation includes over… 2,000 students With 20 teachers/classes At 6 schools 11/9/2018 ASSISTment

ASSISTment Tutoring System Students attempt to answer top level questions based on previous MCAS test questions If the student answers incorrectly or asks for a “hint” they are given supporting questions, called scaffolds, or hint text messages All answers and actions are logged on the server 11/9/2018 ASSISTment

The Task To use Bayesian networks to assess students’ knowledge levels in the ASSISTment system and predict their performance on the MCAS test. Research topic: Compare predictive performance of fine-grain vs. coarse-grain skill models. 11/9/2018 ASSISTment

Bayesian Networks "The essence of the Bayesian approach is to provide a mathematical rule explaining how you should change your existing beliefs in the light of new evidence. In other words, it allows scientists to combine new data with their existing knowledge or expertise.” - The Economist (9/30/00) 11/9/2018 ASSISTment

Bayesian Networks “New data” “Existing knowledge or expertise” 2,000 students answering questions online MCAS test results “Existing knowledge or expertise” Various grain skill models Prof. Neil Heffernan Bayes Rule: Where ‘R’ is a random variable with value ‘r’ and evidence ‘e’ 11/9/2018 ASSISTment

Platform Selection Bayesian network software choices: GeNIe MSBNx BayesiaLab Netica MATLAB with BNT (Bayes Net Toolkit) Java Bayes 11/9/2018 ASSISTment

Platform selection Choice: MATLAB with BNT Pros: Cons Provides wide selection of inference engines MATLAB’s robust programming environment Automation Runs on GNU/Linux Existing Perl interface for the many scripts that will perform data mining tasks. Cons Little Slow 11/9/2018 ASSISTment

Project Overview The datasets Skill models Parameters Implementation Results 11/9/2018 ASSISTment

The Datasets Student online response data 600 students from 2004-2005 Student selection criteria: Completed at least 100 items online Completed the 2005 MCAS test 2,568 question items Student state MCAS test scores for ’05 Used for calculating prediction accuracy No test data used for training/parameter learning 11/9/2018 ASSISTment

Skill Models Skill models describe the skills which are related to the online and MCAS questions. Skill models used: MCAS1 MCAS5 MCAS39 WPI106 11/9/2018 ASSISTment

Skill Models Skill models used for the MCAS test consisting of 29 multiple choice questions MCAS1 MCAS5 11/9/2018 ASSISTment

Skill Models MCAS39 WPI106 The MCAS1 is a two layer network with skill nodes mapped to question nodes. The other 3 networks have a third, intermediary layer of ‘AND’ nodes. This allows all question nodes to have the same number of parameters (slip/guess). The ‘AND’ nodes also reflect the notion that a student must know all tagged skills to answer the item correct. 11/9/2018 ASSISTment

Skill Models Transfer table for skill models 11/9/2018 ASSISTment WPI-106 WPI-39 WPI-5 WPI-1 Equation-concept setting-up-and-solving-equations Patterns-Relations-Algebra The skill of “math” Plot Graph modeling-covariation Slope understanding-line-slope-concept Similar Triangles understanding-and-applying-congruence-and-similarity Geometry Perimeter Circumference Area using-measurement-formulas-and-techniques Equation-Solving Inequality-solving X-Y-Graph Congruence 11/9/2018 ASSISTment

Parameters Parameters were set as a best guess starting point. Test model guess parameter is 0.25 because questions are multiple choice (out of four) Original Parameters Online Model Test Model Skills 0.50 Imported Guess 0.10 0.25 Slip 0.05 Learned Parameters Online Model Skills 0.44 Guess 0.30 Slip 0.38 Preliminary learning of parameters using EM on the MCAS1 network indicates a guess of 0.30, slip of 0.38 and prior of 0.44 on the skills. These numbers were calculated recently and are not used in our prediction results thus far. 11/9/2018 ASSISTment

Implementation The main routine ‘bn_eval()’ takes in: Name of skill model StudentID BNT object of the skill model bayes net ‘bn_eval()’ outputs: Status messages Predicted score/Actual score/Accuracy Logs prediction and skill assessment data 11/9/2018 ASSISTment

Implementation The evaluation is a 2 stage process Stage 1 Bayes skill model for the online data is loaded Student’s online results are compiled and sequenced for the network Student is given credit for all scaffold questions relating to a top level item answered correctly Results are entered into the network as evidence Marginals on the skill nodes are calculated using liklihood_weighting approximate inference . 11/9/2018 ASSISTment

Implementation Stage 2 of evaluation Bayes skill model for the MCAS test is loaded Skill marginals calculated from stage 1 are entered into the test model as soft evidence Marginals on the question nodes are calculated using jtree (join-tree) exact inference. Test score points are summed by multiplying each marginal by 1 and then taking the ceiling of the total score. Predicted test score is compared to actual student test score. 11/9/2018 ASSISTment

Implementation Example student run using MCAS1 model 11/9/2018 ASSISTment

Implementation Assessed skill marginals using MCAS1 11/9/2018 ASSISTment

Implementation Example student run using MCAS5 model 11/9/2018 ASSISTment

Implementation Assessed skill marginals using MCAS5 11/9/2018 ASSISTment

Implementation Example student run using MCAS39 model 11/9/2018 ASSISTment

Implementation Assessed skill marginals using MCAS39 11/9/2018 ASSISTment

Implementation Example student run using WPI106 model 11/9/2018 ASSISTment

Implementation Assessed skill marginals using WPI106 11/9/2018 ASSISTment

Results Model performance/accuracy results: MAD is Mean Average Difference. The test is out of 29 points so a MAD score of 4.5 indicates that the model on average predicts a score that is 4.5 points from the actual score. MODEL MAD (RAW) % ERROR WPI-39 4.500 15.00 % WPI-106 4.970 16.57 % WPI-5 5.295 17.65 % WPI-1 7.700 25.67 % 11/9/2018 ASSISTment

Future Work Reduce runtime Increase accuracy Optimize the number of samples used with liklihood_weighting inference for each model. Increase accuracy Learn full parameters in all models Use analysis to improve skill model tagging Experiment with alternative models Combine skill models into a hierarchy Introduce time as a variable (DBNs) 11/9/2018 ASSISTment

References A copy of this presentation as well as our initial paper submitted to ITS2006 entitled “Using Fine-Grained Skill Models to Fit Student Performance with Bayesian Networks” can be found online at: http://users.wpi.edu/~zpardos/bayes.html Thanks to the WPI-CS department, Neil Heffernan, contributors at CMU and the ASSISTment developers. 11/9/2018 ASSISTment