Presentation is loading. Please wait.

Presentation is loading. Please wait.

Using Bayesian Networks to Predict Test Scores

Similar presentations


Presentation on theme: "Using Bayesian Networks to Predict Test Scores"— Presentation transcript:

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

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

3 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

4 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

5 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

6 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

7 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

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

9 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

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

11 The Datasets Student online response data
600 students from 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

12 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

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

14 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

15 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

16 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

17 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

18 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

19 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

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

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

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

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

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

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

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

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

28 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

29 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

30 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: Thanks to the WPI-CS department, Neil Heffernan, contributors at CMU and the ASSISTment developers. 11/9/2018 ASSISTment


Download ppt "Using Bayesian Networks to Predict Test Scores"

Similar presentations


Ads by Google