ECG-based affective computing for difficulty level prediction in Intelligent Tutoring Systems

Abstract

Intelligent tutoring Systems (ITS) have emerged as an attractive solution for providing personalised learning experiences on a large scale. Traditional ITS are able to adapt the learning process according to the capabilities and needs of their users, but lack the capability to adapt to their affective/emotional state. In this work, we examine the use of electrocardiography (ECG) signals for detecting the affective state of ITS users. Features, extracted from ECG signals acquired while users undertook a computerised English language test, were used for the prediction of the self-reported difficulty level of the test's questions. Supervised classification experiments demonstrated the potential of this approach, achieving a classification F1-score of 61.22% for the prediction of the self-assessed difficulty level of the questions.

In-process feedback by detecting deadlock based on EEG data in exercise of learning by problem- posing and its evaluation

“…Affective computing not only identifies the facial expressions of the learner through a camera, it also facilitates the acquisition of physiological information through recent advances in measurement technology. Therefore, attempts have been made to estimate the emotional aspects of learners using an electrocardiogram (Alqahtani et al, 2019) and an EEG (Xu et al, 2018). In addition, recent research has attempted to use deep learning algorithms to estimate the emotional state of learners using multidimensional physiological information from multiple devices (Matsui et al, 2019).…”

Using Wearable Physiological Sensors for Affect-Aware Intelligent Tutoring Systems

“…Looking through the available literature, it is evident that the use of physiological signals in the field of ITS is focused mainly on emotion recognition and ITS adaptation. Based on this and to the best of the authors' knowledge, our preliminary work [26], [27] and this work are the first that attempted to establish the relation between physiological signals and the self-assessed difficulty level of answered test questions, as well as the success rate in answering the examined questions.…”

“…In this work, we expanded our preliminary work [26], [27] and studied the potential use of EEG, ECG, and EMG physiological signals for detecting the affective state of users participating in a computerised English language test. The aim of the study was to examine whether features extracted by the aforementioned physiological signals are related to the difficulty level of each test question as perceived by the test takers during the test, and whether they can be used as an indicator of the success of the test taker in answering a test question.…”