Analyzing teacher-student interactions through graph theory applied to hyperscanning fNIRS data.

Teacher-student relationships have been found consistently important for student school effectiveness in mathematics in the last three decades. Although this observation is generally made from the teacher's perspective, neuroscience can provide new insights by establishing the neurobiological underpinning of social interactions. This paper further develops this line of research by utilizing graph theory to represent interactions between teachers and students at the neural level. Through hyperscanning with functional near-infrared spectroscopy (fNIRS), we collected data from the prefrontal cortex and the temporoparietal junction of 24 dyads composed of a teacher and a student. Each dyad used a board game to perform a programming logic class that consisted of three steps: independent activities (control), presentation of concepts, and interactive exercises. Graph theory provides results regarding the strength of teacher-student interaction and the main channels involved in these interactions. We combined graph modularity and bootstrap to measure pair coactivation, thus establishing the strength of teacher-student interaction. Also, graph centrality detects the main brain channels involved during this interaction. In general, the teacher's most relevant nodes rely on the regions related to language and number processing, spatial cognition, and attention. Also, the students' most relevant nodes rely on the regions related to task management.

Exploring the potential of eye tracking on personalized learning and real-time feedback in modern education.

Eye tracking is one of the techniques used to investigate cognitive mechanisms involved in the school context, such as joint attention and visual perception. Eye tracker has portability, straightforward application, cost-effectiveness, and infant-friendly neuroimaging measures of cognitive processes such as attention, engagement, and learning. Furthermore, the ongoing software enhancements coupled with the implementation of artificial intelligence algorithms have improved the precision of collecting eye movement data and simplified the calibration process. These characteristics make it plausible to consider eye-tracking technology a promising tool to assist the teaching-learning process in school routines. However, eye tracking needs to be explored more as an educational instrument for real-time classroom activities and teachers' feedback. This perspective article briefly presents the fundamentals of the eye-tracking technique and four illustrative examples of employing this method in everyday school life. The first application shows how eye tracker information may contribute to teacher assessment of students' computational thinking in coding classes. In the second and third illustrations, we discuss the additional information provided by the eye-tracker to the teacher assessing the student's strategies to solve fraction problems and chart interpretation. The last illustration demonstrates the potential of eye tracking to provide Real-time feedback on learning difficulties/disabilities. Thus, we highlight the potential of the eye tracker as a complementary tool to promote personalized education and discuss future perspectives. In conclusion, we suggest that an eye-tracking system could be helpful by providing real-time student gaze leading to immediate teacher interventions and metacognition strategies.

Análise da Viabilidade de Uso do FNIRS em Atividades Educacionais com Crianças e Jovens com Deficiência Intelectual e Autismo / Analysis of FNIRS Usability in Educational Activities with Children and Young People with Intellectual Disability and Autism

RESUMO: Métodos em neurociência cognitiva podem auxiliar o planejamento educacional de docentes no contexto da Educação Especial, por favorecerem práticas personalizadas que valorizem a velocidade individual de aprendizagem de estudantes com transtorno do espectro do autismo (TEA) e/ou deficiência intelectual (DI). Assim sendo, este estudo objetivou verificar a viabilidade de uso da Espectroscopia Funcional de Infravermelho Próximo (fNIRS) em situação naturalística clínica com crianças e jovens com TEA e/ou DI durante tarefas de ensino. Ademais, o estudo buscou identificar as estratégias de treino para que as crianças e os jovens utilizassem o equipamento durante a realização da atividade. Sete estudantes com diagnóstico de TEA e/ou DI foram treinados com atividades de matemática, leitura e expressividade emocional, de acordo com seus respectivos currículos educacionais prévios. Cada participante foi exposto a duas tarefas em cada atividade, uma na qual já apresentava domínio e outra que necessitava de apoio para emitir uma resposta independente. Os resultados indicaram a viabilidade de uso do fNIRS nesse contexto natural da criança e do jovem e forneceram medidas implícitas para além das medidas observacionais de acerto e erro na tarefa. Esta é uma importante demonstração da viabilidade do uso do fNIRS em experimentos no contexto da Educação Especial.

ABSTRACT: Methods in cognitive neuroscience can assist educational planning of teachers in the context of Special Education, as they favor personalized practices that value individual students with Autism Spectrum Disorder (ASD) and/or Intellectual Deficiency (ID). Therefore, this study aimed to verify the feasibility of using functional near-infrared spectroscopy (fNIRS) in clinical naturalistic situation with children and young people with ASD and/or ID during teaching tasks. In addition, the study sought to identify training strategies so that children and young people use the equipment during the activity. Seven students diagnosed with ASD and/or ID were trained with mathematics, reading and emotional expressiveness, according to their respective previous educational curricula. Each participant was exposed to two tasks in each activity, one in which he/she already had a domain and one that needed support to issue an independent response. The results indicated the feasibility of using fNIRS in this natural context of the child and the young student and provided implicit measures beyond the observational arrangement measures and task error. This is an important demonstration of the feasibility of using fNIRS in experiments in the context of Special Education.

Applications of graph theory to the analysis of fNIRS data in hyperscanning paradigms.

Hyperscanning is a promising tool for investigating the neurobiological underpinning of social interactions and affective bonds. Recently, graph theory measures, such as modularity, have been proposed for estimating the global synchronization between brains. This paper proposes the bootstrap modularity test as a way of determining whether a pair of brains is coactivated. This test is illustrated as a screening tool in an application to fNIRS data collected from the prefrontal cortex and temporoparietal junction of five dyads composed of a teacher and a preschooler while performing an interaction task. In this application, graph hub centrality measures identify that the dyad's synchronization is critically explained by the relation between teacher's language and number processing and the child's phonological processing. The analysis of these metrics may provide further insights into the neurobiological underpinnings of interaction, such as in educational contexts.

Predicting Student Performance Using Machine Learning in fNIRS Data.

Increasing student involvement in classes has always been a challenge for teachers and school managers. In online learning, some interactivity mechanisms like quizzes are increasingly used to engage students during classes and tasks. However, there is a high demand for tools that evaluate the efficiency of these mechanisms. In order to distinguish between high and low levels of engagement in tasks, it is possible to monitor brain activity through functional near-infrared spectroscopy (fNIRS). The main advantages of this technique are portability, low cost, and a comfortable way for students to concentrate and perform their tasks. This setup provides more natural conditions for the experiments if compared to the other acquisition tools. In this study, we investigated levels of task involvement through the identification of correct and wrong answers of typical quizzes used in virtual environments. We collected data from the prefrontal cortex region (PFC) of 18 students while watching a video lecture. This data was modeled with supervised learning algorithms. We used random forests and penalized logistic regression to classify correct answers as a function of oxyhemoglobin and deoxyhemoglobin concentration. These models identify which regions best predict student performance. The random forest and penalized logistic regression (GLMNET with LASSO) obtained, respectively, 0.67 and 0.65 area of the ROC curve. Both models indicate that channels F4-F6 and AF3-AFz are the most relevant for the prediction. The statistical significance of these models was confirmed through cross-validation (leave-one-subject-out) and a permutation test. This methodology can be useful to better understand the teaching and learning processes in a video lecture and also provide improvements in the methodologies used in order to better adapt the presentation content.