Abstract
Capturing data on socio-spatial behaviours is essential in obtaining meaningful educational insights into collaborative learning and teamwork in co-located learning contexts. Existing solutions, however, have limitations regarding scalability and practicality since they rely largely on costly location tracking systems, are labour-intensive, or are unsuitable for complex learning environments. To address these limitations, we propose an innovative computer-vision-based approach – Computer Vision for Position Estimation (CVPE) – for collecting socio-spatial data in complex learning settings where sophisticated collaborations occur. CVPE is scalable and practical with a fast processing time and only needs low-cost hardware (e.g., cameras and computers). The built-in privacy protection modules also minimise potential privacy and data security issues by masking individuals’ facial identities and provide options to automatically delete recordings after processing, making CVPE a suitable option for generating continuous multimodal/classroom analytics. The potential of CVPE was evaluated by applying it to analyse video data about teamwork in simulation-based learning. The results showed that CVPE extracted socio-spatial behaviours relatively reliably from video recordings compared to indoor positioning data. These socio-spatial behaviours extracted with CVPE uncovered valuable insights into teamwork when analysed with epistemic network analysis. The limitations of CVPE for effective use in learning analytics are also discussed.
Links
BibTeX (Download)
@inproceedings{li2024cpve,
title = {CVPE: A Computer Vision Approach for Scalable and Privacy-Preserving Socio-Spatial, Multimodal Learning Analytics},
author = {Xinyu Li and Lixiang Yan and Linxuan Zhao and Roberto Martinez-Maldonado and Dragan Gasevic},
url = {https://doi.org/10.1145/3576050.3576145},
doi = {10.1145/3576050.3576145},
isbn = {9781450398657},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {LAK23: 13th International Learning Analytics and Knowledge Conference},
pages = {175–185},
publisher = {Association for Computing Machinery},
address = {Arlington, TX, USA},
series = {LAK2023},
abstract = {Capturing data on socio-spatial behaviours is essential in obtaining meaningful educational insights into collaborative learning and teamwork in co-located learning contexts. Existing solutions, however, have limitations regarding scalability and practicality since they rely largely on costly location tracking systems, are labour-intensive, or are unsuitable for complex learning environments. To address these limitations, we propose an innovative computer-vision-based approach – Computer Vision for Position Estimation (CVPE) – for collecting socio-spatial data in complex learning settings where sophisticated collaborations occur. CVPE is scalable and practical with a fast processing time and only needs low-cost hardware (e.g., cameras and computers). The built-in privacy protection modules also minimise potential privacy and data security issues by masking individuals’ facial identities and provide options to automatically delete recordings after processing, making CVPE a suitable option for generating continuous multimodal/classroom analytics. The potential of CVPE was evaluated by applying it to analyse video data about teamwork in simulation-based learning. The results showed that CVPE extracted socio-spatial behaviours relatively reliably from video recordings compared to indoor positioning data. These socio-spatial behaviours extracted with CVPE uncovered valuable insights into teamwork when analysed with epistemic network analysis. The limitations of CVPE for effective use in learning analytics are also discussed.},
keywords = {collaborative learning, computer vision, epistemic network, learning analytics, multimodality},
pubstate = {published},
tppubtype = {inproceedings}
}
