2026-04-14T19:26:32Zhttps://uvadoc.uva.es/oai/request

oai:uvadoc.uva.es:10324/744122025-09-04T12:05:23Zcom_10324_1165com_10324_931com_10324_894col_10324_1335

Prieto Santos, Luis Pablo Sharma, Kshitij Kidzinski, Łukasz Rodríguez Triana, María Jesús Dillenbourg, Pierre 2025-01-27T02:00:24Z 2025-01-27T02:00:24Z 2018 Journal of Computer Assisted Learning, April 2018, vol. 34, n. 2, p.193-203 https://uvadoc.uva.es/handle/10324/74412 10.1111/jcal.12232 193 2 203 Multimodal teaching analytics: Automated extraction of orchestration graphs from wearable sensor data 34 The pedagogical modelling of everyday classroom practice is an interesting kind of evidence, both for educational research and teachers' own professional development. This paper explores the usage of wearable sensors and machine learning techniques to automatically extract orchestration graphs (teaching activities and their social plane over time) on a dataset of 12 classroom sessions enacted by two different teachers in different classroom settings. The dataset included mobile eye-tracking as well as audiovisual and accelerometry data from sensors worn by the teacher. We evaluated both time-independent and time-aware models, achieving median F1 scores of about 0.7–0.8 on leave-one-session-out k-fold cross-validation. Although these results show the feasibility of this approach, they also highlight the need for larger datasets, recorded in a wider variety of classroom settings, to provide automated tagging of classroom practice that can be used in everyday practice across multiple teachers. eng info:eu-repo/semantics/embargoedAccess Wiley Online Library Multimodal teaching analytics: Automated extraction of orchestration graphs from wearable sensor data info:eu-repo/semantics/article