Mapping from proximity traces to socio‐spatial behaviours and student progression at the school

Abstract

AbstractIdentifying students facing difficulties and providing them with timely support is one of the educator's key responsibilities. Yet, this task is becoming increasingly challenging as the complexity of physical learning spaces grows, along with the emergence of novel educational technologies and classroom designs. There has been substantial research and development work focused on identifying student social behaviours in digital platforms (eg, the learning management system) as predictors of academic progression. However, little work has investigated such relationships in physical learning spaces. This study explores the potential of using wearable trackers for the early detection of low‐progress students based on their social and spatial (socio‐spatial) behaviours at the school. Positioning data from 98 primary school students and six teachers were automatically captured over a period of eight weeks. Fourteen socio‐spatial behavioural features were extracted and processed using a set of machine learning classifiers to model students’ learning progression. Results illustrate the potential of prospectively identifying low‐progress students from these features and the importance of adapting classroom learning analytics to differences in pedagogical designs. Practitioner notesWhat is already known about this topic Learning analytics research on predicting students’ academic progression is emerging in both digital and physical learning spaces. Students’ social behaviours in learning activities is a key factor in predicting their academic progression. Emerging sensing technologies can provide opportunities to study students’ real‐time social behaviours in physical learning spaces. What this paper adds Fourteen progression‐related socio‐spatial behavioural features are extracted from students’ physical (x‐y) positioning traces. Predictive learning analytics that achieved 81% accuracy in prospectively identifying low‐progress students from their real‐time socio‐spatial behaviours. Empirical evidence to support the need for classroom learning analytics to have instructional sensitivity (ie, be calibrated according to the learning design). Implications for practice and/or policy Sensing technologies and machine learning algorithms can be used to capture and generate valuable insights about higher‐order learning constructs (eg, performance and collaboration) from students' physical positioning traces in classrooms. Researchers and practitioners should be cautious with generalised classification algorithms and predictive learning analytics that do not account for the pedagogical differences between different subjects or learning designs. Researchers and practitioners should consider the potentially unforeseen ethical issues that can emerge in using sensing technologies and predictive learning analytics in authentic, physical classroom settings.