AI-based Multimodal Biometrics for Detecting Smartphone Distractions: Application to Online Learning

TL;DR

This paper presents an AI-based multimodal biometric system that detects smartphone-induced distractions in online learning by analyzing physiological signals and head pose, achieving up to 91% accuracy.

Contribution

It introduces a multimodal biometric approach combining biosensors and head pose data to accurately detect smartphone distractions during online learning.

Findings

Head pose alone achieves 87% accuracy.

Multimodal model reaches 91% accuracy.

Single biosignals like brain waves or heart rate are less accurate.

Abstract

This work investigates the use of multimodal biometrics to detect distractions caused by smartphone use during tasks that require sustained attention, with a focus on computer-based online learning. Although the methods are applicable to various domains, such as autonomous driving, we concentrate on the challenges learners face in maintaining engagement amid internal (e.g., motivation), system-related (e.g., course design) and contextual (e.g., smartphone use) factors. Traditional learning platforms often lack detailed behavioral data, but Multimodal Learning Analytics (MMLA) and biosensors provide new insights into learner attention. We propose an AI-based approach that leverages physiological signals and head pose data to detect phone use. Our results show that single biometric signals, such as brain waves or heart rate, offer limited accuracy, while head pose alone achieves 87%. A multimodal model combining all signals reaches 91% accuracy, highlighting the benefits of integration. We conclude by discussing the implications and limitations of deploying these models for real-time support in online learning environments.