Automatic Detection of User' Uncertainty in Problem Solving Task: a Multimodal Approach

This paper presents a novel multimodal approach to automatically detect learner uncertainty through the integration of multiple sensors. An acquisition protocol was established for the recording of learner electrical brain activity and physiological signals while interacting with a problem solving system specifically designed for uncertainty elicitation. Data were collected from 38 subjects using 8 sensors and two video feeds. Results from machine learning classifiers support the feasibility of our approach. 81% of accuracy was reached using Support Vector Machine (SVM) algorithm.