|
on Neuroeconomics |
| By: | Mohamed Amir Omezzine (EESC-GEM - Grenoble Ecole de Management); Maissa Obay |
| Abstract: | This study investigates how adaptive learning systems, powered by Bayesian Knowledge Tracing and augmented with physiological monitoring, regulate cognitive effort and engagement across digital and non-digital quiz formats. We introduce the Cognitive Elasticity Model, extending Flow Theory and Cognitive Load Theory, to conceptualize how adaptive systems stretch learner effort toward an optimal zone of engagement. A mixed-methods design combines a controlled experiment (N = 180) with Q methodology to map subjective learner profiles across three quiz modalities: adaptive Moodle, static Moodle, and paper-based. Physiological indicators—EEG (frontal theta/alpha ratio) and ECG (heart rate variability)—complement self-reports of flow, cognitive load, and stress. Q-sorting reveals distinct engagement-effort configurations, offering new insight into how learners perceive and respond to adaptive systems. Our contribution is both theoretical—refining non-linear models of cognitive regulation—and pedagogical—proposing a replicable framework for mediating scientific insight into classroom decision-making through neuro-instrumentation and learner-centered profiling. |
| Date: | 2026–05–20 |
| URL: | https://d.repec.org/n?u=RePEc:hal:gemptp:hal-05789339 |
| By: | Mohamed Amir Omezzine (EESC-GEM - Grenoble Ecole de Management) |
| Abstract: | Adaptive quizzes are increasingly used to individualize practice in digital learning, but IS research still under-specifies how AI-driven adaptivity regulates student effort during task performance. This paper addresses that gap by proposing the Cognitive Elasticity Model, which explains learning engagement as depending not only on challenge-skill balance or cognitive load alone, but on the learner's capacity to remain within a productive effort zone as task demands shift. Grounded in Flow Theory and Cognitive Load Theory, the model positions adaptive quizzing as a system-level mechanism for regulating effort over time rather than only improving assessment efficiency. The study examines this claim through a three-condition experiment with 180 students: a Moodle adaptive quiz using Bayesian Knowledge Tracing, a non-adaptive Moodle quiz with identical items and timing, and an equivalent paper-based quiz. Cognitive load and flow are assessed primarily through phase-level self-report measures. These are complemented by EEG-derived indicators, including the Cognitive Load Score (CLS) for workload regulation and theta/alpha markers associated with flow-related engagement, while physiological strain is assessed through repeated ECG-based mean heart rate snapshots interpreted conservatively as indicators of stress-related arousal rather than direct readouts of internal states. |
| Abstract: | Les quiz adaptatifs sont de plus en plus utilisés pour individualiser la pratique dans les environnements d'apprentissage numérique. Cependant, la recherche en systèmes d'information explique encore insuffisamment la manière dont l'adaptativité pilotée par l'IA régule l'effort des étudiants pendant la réalisation d'une tâche. Cet article répond à cette limite en proposant le modèle d'élasticité cognitive. Ce modèle considère que l'engagement dans l'apprentissage ne dépend pas seulement de l'équilibre entre défi et compétence, ni du niveau de charge cognitive pris isolément, mais de la capacité de l'étudiant à maintenir son effort dans une zone productive lorsque les exigences de la tâche évoluent. |
| Date: | 2026–05–20 |
| URL: | https://d.repec.org/n?u=RePEc:hal:gemptp:hal-05789341 |
| By: | Lucía Canalejo Guijosa (Banco de España); Fernando León Martínez (Banco de España); José María Sánchez Echave (Banco de España) |
| Abstract: | Situated within the Neurocash ® framework for measuring implicit emotional and cognitive responses, this review examines the human voice as a non-invasive psychophysiological marker. It outlines the physiological mechanisms of voice production and explains how emotional states influence breathing, vocal-fold vibration and articulation, shaping acoustic features such as pitch and intensity. The review then examines Speech Emotion Recognition as the main approach for extracting emotional information from speech, describing the methodological pipeline from emotional speech databases and preprocessing to classification using traditional machine-learning algorithms and modern deep-learning and self-supervised models. The analysis concludes that no single computational approach is universally optimal, as performance depends on language, emotional categories, data quality and environmental conditions. Overall, this review provides an interdisciplinary framework linking psychophysiology, vocal acoustics and artificial intelligence to support Neurocash ® studies on cognitive workload, perceived security and implicit trust in cash design. |
| Keywords: | acoustic feature extraction, affective computing, implicit emotion perception, multimodal emotion analysis, psychophysiology, self-supervised representation learning, Speech Emotion Recognition, Neurocash ®, cash design |
| JEL: | C55 C80 D91 |
| Date: | 2026–09 |
| URL: | https://d.repec.org/n?u=RePEc:bde:opaper:2618e |