A factorization approach to evaluate open-response assignments in MOOCs using preference learning on peer assessments

作者：

Highlights：

• We approach the problem of assessing open-text questions in MOOCs by peer-assessment.

• Our method avoids the intrinsic subjectivity of the numeric grades given by graders.

• Experiments where made with real-world data collected from 3 Universities in Spain.

• Our method performs well when comparing discrepancies among instructors’ grades.

摘要

•We approach the problem of assessing open-text questions in MOOCs by peer-assessment.•Our method avoids the intrinsic subjectivity of the numeric grades given by graders.•Experiments where made with real-world data collected from 3 Universities in Spain.•Our method performs well when comparing discrepancies among instructors’ grades.

论文关键词：Peer grading,Factorization,Preference learning,Ordinal and cardinal approaches,MOOCs

论文评审过程：Received 11 December 2014, Revised 17 April 2015, Accepted 17 May 2015, Available online 21 May 2015, Version of Record 16 July 2015.

论文官网地址：https://doi.org/10.1016/j.knosys.2015.05.019