Machine learning models are widely used to support stealth assessment in digital learning environments. Existing approaches typically rely on abstracted gameplay log data, which may overlook subtle behavioral cues linked to learners' cognitive strategies. This paper proposes a multimodal late fusion model that integrates screencast-based visual data and structured in-game action sequences to classify students' problem-solving strategies. In a pilot study with secondary school students (N=149) playing a multitouch educational game, the fusion model outperformed unimodal baseline models, increasing classification accuracy by over 15%. Results highlight the potential of multimodal ML for strategy-sensitive assessment and adaptive support in interactive learning contexts.
@article{arxiv.2507.22426,
title = {Multimodal Late Fusion Model for Problem-Solving Strategy Classification in a Machine Learning Game},
author = {Clemens Witt and Thiemo Leonhardt and Nadine Bergner and Mareen Grillenberger},
journal= {arXiv preprint arXiv:2507.22426},
year = {2025}
}
Comments
This is the author's version of a paper accepted for publication at the 2025 European Conference on Technology Enhanced Learning (EC-TEL 2025). The final authenticated version will be published in the Lecture Notes in Computer Science (LNCS) series by Springer and will be available via SpringerLink