PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
January 1, 2012Applied Measurement in Education144 citations

Comparison of Human and Machine Scoring of Essays: Differences by Gender, Ethnicity, and Country

View Full Paper
BBBrent BridgemanCTCatherine TrapaniYAYigal Attali

Key Points

  • To determine whether automated machine essay scoring produces disparate outcomes compared to human rater scoring across distinct gender, ethnic, and country subgroups.
  • Analyzed essay scoring data from two large-scale standardized assessments: the Test of English as a Foreign Language (TOEFL) and the Graduate Record Examination (GRE).
  • Compared score distributions, means, standard deviations, and correlations between automated scoring algorithms and human raters across demographic subgroups.
  • Machine-generated scores generally aligned with human rater scores in both distribution and inter-rater correlation across the majority of evaluated subgroups.
  • Identified notable score discrepancies between machine and human scoring in a limited number of specific demographic groups.
  • Established score-reporting policies to minimize the practical impact of machine-human scoring discrepancies on final reported scores.

Abstract

Essay scores generated by machine and by human raters are generally comparable; that is, they can produce scores with similar means and standard deviations, and machine scores generally correlate as highly with human scores as scores from one human correlate with scores from another human. Although human and machine essay scores are highly related on average, this does not eliminate the possibility that machine and human scores may differ significantly for certain gender, ethnic, or country groups. Such differences were explored with essay data from two large-scale high-stakes testing programs: the Test of English as a Foreign Language and the Graduate Record Examination. Human and machine scores were very similar across most subgroups, but there were some notable exceptions. Policies were developed so that any differences between humans and machines would have a minimal impact on final reported scores.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Bridgeman et al. (2012) studied this question.

synapsesocial.com/papers/69dbea49d60f0b8828835af5https://doi.org/10.1080/08957347.2012.635502
Ask AI
Helpful
Bookmark
Share
View Full Paper