This paper describes the analysis of electrodermal activity (EDA) in the context of students’ scholastic activity. Taking a multidisciplinary, citizen science and maker-centric approach, low-cost, bespoken wearables, such as a mini weather station and biometric wristband, were built. To investigate both physical health as well as stress, the instruments were first validated against research grade devices. Following this, a research experiment was created and conducted in the context of students’ scholastic activity. Data from this experiment were used to train machine learning models, which were then applied to interpret the relationships between the environment, health, and stress. It is hoped that analyses of EDA data will further strengthen the emerging model describing the intersections between local microclimate and physiological and neurological stress. The results suggest that temperature and air quality play an important role in students’ physiological well-being, thus demonstrating the feasibility of understanding the extent of the effects of various microclimatic factors. This highlights the importance of thermal comfort and air ventilation in real-life applications to improve students’ well-being. We envision our work making a significant impact by showcasing the effectiveness and feasibility of inexpensive, self-designed wearable devices for tracking microclimate and electrodermal activity (EDA). The affordability of these wearables holds promising implications for scalability and encourages crowd-sourced citizen science in the relatively unexplored domain of microclimate’s influence on well-being. Embracing citizen science can then democratize learning and expedite rapid research advancements.

This paper reports a study conducted by students as an independent research project under the mentorship of a research scientist at the National Institute of Education, Singapore. The aim of the study was to explore the relationships between local environmental stressors and physiological responses from the perspective of citizen science. Starting from July 2021, data from EEG headsets were complemented by those obtained from smartwatches (namely heart rate and its variability and body temperature and stress score). Identical units of a wearable device containing environmental sensors (such as ambient temperature, air pressure, infrared radiation, and relative humidity) were designed and worn, respectively, by five adolescents for the same period. More than 100,000 data points of different types—neurological, physiological, and environmental—were eventually collected and were processed through a random forest regression model and deep learning models. The results showed that the most influential microclimatic factors on the biometric indicators were noise and the concentrations of carbon dioxide and dust. Subsequently, more complex inferences were made from the Shapley value interpretation of the regression models. Such findings suggest implications for the design of living conditions with respect to the interaction of the microclimate and human health and comfort.

The influence of microclimate on the affective state of learners is of interest in the context of anthropogenic climate change. In prior work, these impacts have been documented using electrodermal activity (EDA). This paper extends that approach with a multimodal analysis of neuro-physiological data in the context of scholastic activity with the inclusion of electroencephalography (EEG), facial action units (FAU), EDA, and photoplethysmography (PPG). Our methodology represents a citizen science, neuroergonomic and multi-pronged approach to investigate the relationships between human neuro-physiologic health and mental well-being. In the present study, low-cost, bespoke wearables were assembled, including EEG headsets, and physiological wristbands. EEG was chosen for its potential to offer neuro-physiological insights. EDA was incorporated as a non-invasive method to detect stress and emotional arousal. PPG was utilised as another indicator, being influenced by vascular, cardiac, and autonomic nervous systems. Finally, FAUs were analysed to prove the feasibility of FAUs as a stand-alone source of data which can support other analysis methods. Statistical tests and machine learning models were used to investigate relationships between neuro-physiological data, subjective data and the surrounding environment. Results suggest that features of the multimodal data were significant as they are correlated with environmental factors, and emotional arousal. The specific extent of the influence was also confirmed using Shapley values. With a deeper understanding of the feasibility of a robust multimodal approach, more complex relationships can be investigated with the upscaling of experiments for different age groups, especially children. This pipeline of data analysis could also be improved and enhanced by the usage of AI. Subsequently, there is potential for policy makers, and individuals to improve environments to maximise well-being.

Background: this paper reports an investigation into the cognitive and emotional states of adolescents while learning from an LLM. It seeks to address a relative dearth in empirical evidence which might otherwise facilitate informed decisions being made by curriculum designers, school leaders and policy makers regarding the use of Generative AI, amidst the wider discourse about the effectiveness of AI in teaching and learning. Methods: in this paper, we analyze electrodermal activity (EDA) in the context of students’ scholastic engagement using LLMs in comparison to curated texts. In our 27-min-long experiment, we recorded the EDA of participants learning from both learning methods, for 8 min each. A quiz was also conducted to assess the effectiveness of the learning method. We collected 23 samples of EDA from the experiment, and 42 samples of quiz results. Results: we have found that learning with an LLM results in greater Skin Conductance Response (p = 0.09404), which is linked to more positive emotional valence, and lower Skin Conductance Level (p = 0.09473), which is linked to lower cognitive load, compared to curated texts. We also discovered that learning with an LLM correlates to a higher quiz result (p = 0.02053). While this suggests that learning and absorbing information with an LLM could be more effective than curated texts, results from self-reported data indicate that there are few perceived differences between the effectiveness of LLM and curated texts. Conclusions: this exploratory and preliminary study revealed empirical insights between LLM usage and learning effectiveness in situ via physiological indicators, in contrast to prior work that has adopted post hoc frames over the medium- to long-term.