When measurement meets machine learning
Interpretability and scalability in modelling item difficulty for language assessment
Bibliographic Data
| ID | 22168367 |
|---|---|
| Authors | Karen Dunn (0000-0002-7499-9895, British Council), Karen J Dunn (British Council, English Language Research), Lucy Skidmore (British Council), Thomas Rogers (British Council) |
| Year | 2026 |
| Volume | 11 |
| Publication date | 2026-03-12 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Frontiers in Education (JOURNAL) |
| Journal identifiers | ISSN: 2504-284X • E-ISSN: 2504-284X |
| Publisher | Frontiers Media SA (PUBLISHER • CH) |
| DOI | 10.3389/feduc.2026.1740237 |
| OpenAlex | W7135086317 |
| Language | EN |
| References cited | 35 |
Estimation of item difficulty is essential in language test development, but recent attention has shifted toward the need also to explain and predict it. This has practical implications for item development, adaptive testing, and construct validation. Measurement specialists have traditionally explored factors contributing to item difficulty through explanatory item response theory (EIRT). In language assessment, explaining difficulty remains challenging due to the complex, context-sensitive nature of linguistic constructs. Advances in artificial intelligence (AI), most notably in machine learning (ML) and natural language processing (NLP) have expanded possibilities, offering scalable and flexible solutions, but may compromise interpretability, i.e., the capacity to link results to the underlying construct of ability. In sensitive areas, such as immigration and citizenship, generating validation evidence is critical, giving rise to a pressing need to understand the implications of using ML models in this context. This conceptual paper explores the meeting ground between measurement and machine learning, examining how these traditions converge and diverge in modelling item difficulty. Trade-offs between model interpretability and scalable application are highlighted, and implications discussed in the light of the increasingly interdisciplinary nature of this field, including possibilities offered by hybrid IRT-ML solutions
Computational linguistics · Interpretability · Item response theory · Natural language · Natural language understanding · Scalability · Educational and Psychological Assessments · Psychometric Methodologies and Testing · Student Assessment and Feedback
Multidimensional Item Response Theory
A Rasch Model for Partial Credit Scoring
The linear logistic test model as an instrument in educational research
Estimation of Latent Ability Using a Response Pattern of Graded Scores
Automatic item generation
The Application of Machine Learning to Educational Process Data Analysis
Measurement Properties of a Standardized Elicited Imitation Test
A systematic review of item response theory in language assessment
Applications of the Linear Logistic Test Model in Psychometric Research
A comprehensive review of Rasch measurement in language assessment
What is the best predictor of word difficulty? A case of data mining using random forest
An Introduction to Network Psychometrics
A rating formulation for ordered response categories
| Highly cited | No |
|---|