Beyond binary correctness: Classification of students’ answers in learning systems


This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on


Year of publication 2020
Type Article in Periodical
Magazine / Source User Modeling and User-Adapted Interaction
MU Faculty or unit

Faculty of Informatics

Keywords adaptive learning; student modeling; answer classification; response time
Description Adaptive learning systems collect data on student performance and use them to personalize system behavior. Most current personalization techniques focus on the correctness of answers. Although the correctness of answers is the most straightforward source of information about student state, research suggests that additional data are also useful, e.g., response times, hints usage, or specific values of incorrect answers. However, these sources of data are not easy to utilize and are often used in an ad hoc fashion. We propose to use answer classification as an interface between raw data about student performance and algorithms for adaptive behavior. Specifically, we propose a classification of student answers into six categories: three classes of correct answers and three classes of incorrect answers. The proposed classification is broadly applicable and makes the use of additional interaction data much more feasible. We support the proposal by analysis of extensive data from adaptive learning systems.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.