Multidimensional student skills with collaborative filtering

Yoav Bergner, Saif Rayyan, Daniel Seaton, David E. Pritchard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Despite the fact that a physics course typically culminates in one final grade for the student, many instructors and researchers believe that there are multiple skills that students acquire to achieve mastery. Assessment validation and data analysis in general may thus benefit from extension to multidimensional ability. This paper introduces an approach for model determination and dimensionality analysis using collaborative filtering (CF), which is related to factor analysis and item response theory (IRT). Model selection is guided by machine learning perspectives, seeking to maximize the accuracy in predicting which students will answer which items correctly. We apply the CF to response data for the Mechanics Baseline Test and combine the results with prior analysis using unidimensional IRT.

Original languageEnglish (US)
Title of host publication2012 Physics Education Research Conference
PublisherAmerican Institute of Physics Inc.
Pages74-77
Number of pages4
Volume1513
ISBN (Electronic)9780735411340
DOIs
StatePublished - 2013
Event2012 Physics Education Research Conference, PERC 2012 - Philadelphia, United States
Duration: Aug 1 2012Aug 2 2012

Other

Other2012 Physics Education Research Conference, PERC 2012
CountryUnited States
CityPhiladelphia
Period8/1/128/2/12

Fingerprint

students
machine learning
factor analysis
instructors
grade
physics

Keywords

  • collaborative filtering
  • formative assessment
  • item response theory
  • testing

ASJC Scopus subject areas

  • Physics and Astronomy(all)

Cite this

Bergner, Y., Rayyan, S., Seaton, D., & Pritchard, D. E. (2013). Multidimensional student skills with collaborative filtering. In 2012 Physics Education Research Conference (Vol. 1513, pp. 74-77). American Institute of Physics Inc.. https://doi.org/10.1063/1.4789655

Multidimensional student skills with collaborative filtering. / Bergner, Yoav; Rayyan, Saif; Seaton, Daniel; Pritchard, David E.

2012 Physics Education Research Conference. Vol. 1513 American Institute of Physics Inc., 2013. p. 74-77.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bergner, Y, Rayyan, S, Seaton, D & Pritchard, DE 2013, Multidimensional student skills with collaborative filtering. in 2012 Physics Education Research Conference. vol. 1513, American Institute of Physics Inc., pp. 74-77, 2012 Physics Education Research Conference, PERC 2012, Philadelphia, United States, 8/1/12. https://doi.org/10.1063/1.4789655
Bergner Y, Rayyan S, Seaton D, Pritchard DE. Multidimensional student skills with collaborative filtering. In 2012 Physics Education Research Conference. Vol. 1513. American Institute of Physics Inc. 2013. p. 74-77 https://doi.org/10.1063/1.4789655
Bergner, Yoav ; Rayyan, Saif ; Seaton, Daniel ; Pritchard, David E. / Multidimensional student skills with collaborative filtering. 2012 Physics Education Research Conference. Vol. 1513 American Institute of Physics Inc., 2013. pp. 74-77
@inproceedings{af10dff0c243460eb78acf68efe1f801,
title = "Multidimensional student skills with collaborative filtering",
abstract = "Despite the fact that a physics course typically culminates in one final grade for the student, many instructors and researchers believe that there are multiple skills that students acquire to achieve mastery. Assessment validation and data analysis in general may thus benefit from extension to multidimensional ability. This paper introduces an approach for model determination and dimensionality analysis using collaborative filtering (CF), which is related to factor analysis and item response theory (IRT). Model selection is guided by machine learning perspectives, seeking to maximize the accuracy in predicting which students will answer which items correctly. We apply the CF to response data for the Mechanics Baseline Test and combine the results with prior analysis using unidimensional IRT.",
keywords = "collaborative filtering, formative assessment, item response theory, testing",
author = "Yoav Bergner and Saif Rayyan and Daniel Seaton and Pritchard, {David E.}",
year = "2013",
doi = "10.1063/1.4789655",
language = "English (US)",
volume = "1513",
pages = "74--77",
booktitle = "2012 Physics Education Research Conference",
publisher = "American Institute of Physics Inc.",

}

TY - GEN

T1 - Multidimensional student skills with collaborative filtering

AU - Bergner, Yoav

AU - Rayyan, Saif

AU - Seaton, Daniel

AU - Pritchard, David E.

PY - 2013

Y1 - 2013

N2 - Despite the fact that a physics course typically culminates in one final grade for the student, many instructors and researchers believe that there are multiple skills that students acquire to achieve mastery. Assessment validation and data analysis in general may thus benefit from extension to multidimensional ability. This paper introduces an approach for model determination and dimensionality analysis using collaborative filtering (CF), which is related to factor analysis and item response theory (IRT). Model selection is guided by machine learning perspectives, seeking to maximize the accuracy in predicting which students will answer which items correctly. We apply the CF to response data for the Mechanics Baseline Test and combine the results with prior analysis using unidimensional IRT.

AB - Despite the fact that a physics course typically culminates in one final grade for the student, many instructors and researchers believe that there are multiple skills that students acquire to achieve mastery. Assessment validation and data analysis in general may thus benefit from extension to multidimensional ability. This paper introduces an approach for model determination and dimensionality analysis using collaborative filtering (CF), which is related to factor analysis and item response theory (IRT). Model selection is guided by machine learning perspectives, seeking to maximize the accuracy in predicting which students will answer which items correctly. We apply the CF to response data for the Mechanics Baseline Test and combine the results with prior analysis using unidimensional IRT.

KW - collaborative filtering

KW - formative assessment

KW - item response theory

KW - testing

UR - http://www.scopus.com/inward/record.url?scp=85029282007&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029282007&partnerID=8YFLogxK

U2 - 10.1063/1.4789655

DO - 10.1063/1.4789655

M3 - Conference contribution

AN - SCOPUS:85029282007

VL - 1513

SP - 74

EP - 77

BT - 2012 Physics Education Research Conference

PB - American Institute of Physics Inc.

ER -