M2LADS Demo: A System for Generating Multimodal Learning Analytics Dashboards
Alvaro Becerra, Roberto Daza, Ruth Cobos, Aythami Morales, Julian Fierrez
TL;DR
Multimodal Learning Analytics integration challenges are addressed by M2LADS, a web-based system that synchronizes biosignals and video from learning sessions. It features three modules—Activity Data Processing, Activity Data Management, and Activity Data Visualization—that align data from edBB biosensors (EEG, eye-tracker, heart rate, webcams) and LOGGE activity metadata, apply a $30$-second sliding-window smoothing, and store anonymized data in MongoDB with Dash-based interactive dashboards. This setup enables activity-wise labeling, cross-stream correlations, and synchronized audiovisual viewing to support relabeling and exploratory analysis. It demonstrates practical value for validating biometric signals and comparing learner performance across activities, with support from multiple research projects.
Abstract
We present a demonstration of a web-based system called M2LADS ("System for Generating Multimodal Learning Analytics Dashboards"), designed to integrate, synchronize, visualize, and analyze multimodal data recorded during computer-based learning sessions with biosensors. This system presents a range of biometric and behavioral data on web-based dashboards, providing detailed insights into various physiological and activity-based metrics. The multimodal data visualized include electroencephalogram (EEG) data for assessing attention and brain activity, heart rate metrics, eye-tracking data to measure visual attention, webcam video recordings, and activity logs of the monitored tasks. M2LADS aims to assist data scientists in two key ways: (1) by providing a comprehensive view of participants' experiences, displaying all data categorized by the activities in which participants are engaged, and (2) by synchronizing all biosignals and videos, facilitating easier data relabeling if any activity information contains errors.