Maria Bolsinova, Tilburg University

Early Career Award

One of the most impactful and promising ambitions in educational innovation is the move towards large-scale personalized learning, facilitated by the emergence of online adaptive learning systems (ALS), also known as adaptive learning environments or computer adaptive practice systems. These systems are designed to dynamically adjust the level of practice and instructional content according to each learner’s abilities, as well as other potential characteristics such as learning preferences, interests, and motivation. These systems also provide diagnostic feedback such as which skills and abilities the learner is deficient in, navigational support regarding which skills to work on, and the learning resources to improve these skills. To effectively optimize feedback, instruction, and educational materials, it is essential to have continuously updated, accurate, and reliable assessments of students’ evolving abilities. Consequently, measurement becomes a crucial aspect of ALS. However, measuring change is inherently complex, and the adaptive nature of ALS, combined with the necessity of serving thousands of learners who require ongoing updates to their ability estimates, adds further complexity. These characteristics present significant challenges to traditional psychometric models and algorithms. In this presentation I will discuss these methodological challenges and present some of the solutions that have been developed in the area of psychometrics for adaptive learning in the recent years.

about the speaker

Maria Bolsinova is an assistant professor at Tilburg University, the Netherlands. Maria obtained her Ph.D. from Utrecht University in 2016 after which she worked as a postdoctoral researcher at the University of Amsterdam and a research scientist at ACTNext. Her dissertation entitled ‘Simple models and complex reality: Contributions to item response theory in educational measurement’ has been recognized by the dissertation awards both from the Psychometric Society and the National Council on Measurement in Education. Maria’s research has been devoted to developing advanced psychometric models for the analysis of product and process data from educational tests and to building statistical foundations for measurement in adaptive learning systems. With her research, she aims to develop statistical tools that will improve the quality of educational measurement in practice and help deliver innovative learning and assessment systems.