Confused or not: decoding brain activity and recognizing confusion in reasoning learning using EEG

Abstract

Objective: Confusion is the primary epistemic emotion in the learning process, influencing students' engagement and whether they become frustrated or bored. However, research on confusion in learning is still in its early stages, and there is a need to better understand how to recognize it and what EEG signals indicate its occurrence. The present work investigates confusion during reasoning learning using EEG, and aims to fill this gap with a multidisciplinary approach combining educational psychology, neuroscience and computer science. 
Approach: First, we design an experiment to actively and accurately induce confusion in reasoning. Second, we propose a subjective and objective joint labeling technique to address the label noise issue. Third, to confirm that the confused state can be distinguished from the non-confused state, we compare and analyze the mean band power of confused and unconfused states across five typical bands. Finally, we present an EEG database for confusion analysis, together with benchmark results from conventional (Naive Bayes, SVM, Random Forest, and ANN) and end-to-end (LSTM, ResNet, and EEGNet) machine learning methods.
Main results: Findings revealed: 1. Significant differences in the power of delta, theta, alpha, beta and lower gamma between confused and non-confused conditions; 2. A higher attentional and cognitive load when participants were confused; and 3. The Random Forest algorithm with time-domain features achieved a high accuracy/F1 score (88.06%/0.88 for the subject-dependent approach and 84.43%/0.84 for the subject-independent approach) in the binary classification of the confused and non-confused states.
Significance: The study advances our understanding of confusion and provides practical insights for recognizing and analyzing it in the learning process. It extends existing theories on the differences between confused and non-confused states during learning and contributes to the cognitive-affective model. The research enables researchers, educators, and practitioners to monitor confusion, develop adaptive systems, and test recognition approaches.

FetchEEG: a hybrid approach combining feature extraction and temporal-channel joint attention for EEG-based emotion classification

“…The CAL dataset was first used in [2]. This dataset differed from the typical emotion elicitation process performed using images or videos; instead, it focused on cognitive emotions during the learning process, including four categories: confused, non-confused, guess, and think-right emotions.…”

“…In the subjectdependent experiments, a five-fold cross-validation approach was adopted. In the subject-independent experiments, similar to the approach described in [2], data were split into 70%/30% across subjects. Specifically, in the MAN dataset, data on 14 subjects were used for training, while data on the remaining five subjects were used for testing.…”

“…In the SEED-IV dataset, data on 11 subjects were used for training, and data on the remaining four subjects were used for testing. It should be noted that for the CAL dataset, in line with the approach used in [2], the experiments were conducted for both binary classification (confused and non-confused) and quaternary classification.…”

“…To evaluate the classification performance, this study compared the experimental results of different methods: naive bayes [2], support vector machine (SVM) [27],random forest [50], deep recurrent-CNN for EEG images [51] (referred to as iDRCNN in the remainder of this manuscript), EEGNet [30], DeepConvNet [9], ShallowConvNet [9], and Conformer [18].…”

“…Recently, human emotions have been identified and understood using computers in the fields of medicine, neuroscience, psychology, and affective computing. Particularly, in the fields of medicine and education [1][2][3], emotion recognition can help doctors to treat different diseases, such as autism, anxiety, and certain brain dysfunctions, and assist teachers in analyzing students' cognitive levels during the learning process, providing personalized recommendations for course and exercise content.…”