Footprints at School: Modelling In-class Social Dynamics from Students’ Physical Positioning Traces

Abstract

Schools are increasingly becoming into complex learning spaces where students interact with various physical and digital resources, educators, and peers. Although the field of learning analytics has advanced in analysing logs captured from digital tools, less progress has been made in understanding the social dynamics that unfold in physical learning spaces. Among the various rapidly emerging sensing technologies, position tracking may hold promises to reveal salient aspects of activities in physical learning spaces such as the formation of interpersonal ties among students. This paper explores how granular x-y physical positioning data can be analysed to model social interactions among students and teachers. We conducted an 8-week longitudinal study in which positioning traces of 98 students and six teachers were automatically captured every day in an open-plan public primary school. Positioning traces were analysed using social network analytics (SNA) to extract a set of metrics to characterise students' positioning behaviours and social ties at cohort and individual levels. Results illustrate how analysing positioning traces through the lens of SNA can enable the identification of certain pedagogical approaches that may be either promoting or discouraging in-class social interaction, and students who may be socially isolated. CCS CONCEPTS• Applied computing → Collaborative learning; Computer-assisted instruction; Learning management systems.

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

“…To model this, a four‐step extraction process was performed: Interpersonal distances among all students were extracted by calculating the Euclidean distances between each tag. This step involved calculating all possible pair combinations for each second. A potential instance of social interaction was identified if two or more tags were within one‐meter proximity of each other for more than ten consecutive seconds, as modelled in previous works (Chng et al., 2020; Martinez‐Maldonado, Schulte, et al., 2020; Yan et al., 2021). This ten‐second constraint minimises the false identification of unintended collocation, for example, when teachers are walking around during supervision or two students are passing by each other (Greenberg et al., 2014).…”

“…Similarly, Yan et al. (2021) also used wearable trackers in the form of wristbands to capture individual social interactions and group social dynamics in large learning spaces, but their discussion limited to model behaviours for descriptive purposes using unsupervised techniques.…”

“…As sensing technologies are becoming ready for their widespread use in educational applications (Chua et al., 2019), analysing students’ physical positioning data traces can be a promising direction to characterise students’ social and spatial behaviours (socio‐spatial) in the classroom. These traces can serve to extract indicators of student interaction with peers and teachers (Chng et al., 2020; Martinez‐Maldonado, Echeverria, et al, 2020; Yan et al., 2021), physical activity (Saquib et al., 2018), sustained engagement (Chin et al., 2017; Chng et al., 2020), and help‐seeking behaviours (Fernandez Nieto et al, 2021), all closely related to learning progression.…”

Transmission of SARS-CoV-2 in a primary school setting with and without public health measures using real-world contact data: A modelling study

“…Close contacts were identified using a proximity-based identification method relying on the Euclidean distances between two participants [39,40]. Two different criteria items were used, both adapted from the guidelines of the Department of Health and Human Services in Victoria [41], which have also been applied in a recent COVID-19 study with Australian children [8].…”

Privacy-Driven Learning Analytics

“…Specifically, novel methods allow for collecting learners' physiological states and behaviours (e.g. heart, brain, skin) (Larmuseau et al, 2020), or capturing social proximity (Yan et al, 2021) and environmental conditions (e.g. location, noise) (Crescenzi-Lanna, 2020).…”