Predicting article quality scores with machine learning: The UK Research Excellence Framework

TL;DR

This study explores using machine learning models to predict article quality scores from the UK Research Excellence Framework 2021, showing promising results in some scientific fields but limited accuracy in others.

Contribution

It demonstrates the potential of AI-based bibliometric models for research evaluation, highlighting their varying effectiveness across disciplines.

Findings

Highest accuracy in medical and physical sciences UoAs (72% overall)

Prediction accuracy improved with active learning strategies

Lower accuracy observed in social sciences, arts, and humanities

Abstract

National research evaluation initiatives and incentive schemes have previously chosen between simplistic quantitative indicators and time-consuming peer review, sometimes supported by bibliometrics. Here we assess whether artificial intelligence (AI) could provide a third alternative, estimating article quality using more multiple bibliometric and metadata inputs. We investigated this using provisional three-level REF2021 peer review scores for 84,966 articles submitted to the UK Research Excellence Framework 2021, matching a Scopus record 2014-18 and with a substantial abstract. We found that accuracy is highest in the medical and physical sciences Units of Assessment (UoAs) and economics, reaching 42% above the baseline (72% overall) in the best case. This is based on 1000 bibliometric inputs and half of the articles used for training in each UoA. Prediction accuracies above the baseline for the social science, mathematics, engineering, arts, and humanities UoAs were much lower or close to zero. The Random Forest Classifier (standard or ordinal) and Extreme Gradient Boosting Classifier algorithms performed best from the 32 tested. Accuracy was lower if UoAs were merged or replaced by Scopus broad categories. We increased accuracy with an active learning strategy and by selecting articles with higher prediction probabilities, as estimated by the algorithms, but this substantially reduced the number of scores predicted.