Multidimensional student skills with collaborative filtering

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

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


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
EditorsN. Sanjay Rebello, Paula V. Engelhardt, Alice D. Churukian
PublisherAmerican Institute of Physics Inc.
Number of pages4
ISBN (Electronic)9780735411340
StatePublished - 2013
Event2012 Physics Education Research Conference, PERC 2012 - Philadelphia, United States
Duration: Aug 1 2012Aug 2 2012

Publication series

NameAIP Conference Proceedings
ISSN (Print)0094-243X
ISSN (Electronic)1551-7616


Other2012 Physics Education Research Conference, PERC 2012
Country/TerritoryUnited States


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

ASJC Scopus subject areas

  • General Physics and Astronomy


Dive into the research topics of 'Multidimensional student skills with collaborative filtering'. Together they form a unique fingerprint.

Cite this