Enhancing Adaptive Learning Through Spectrum of Individuality Theory: A Neuroplasticity-Informed AI Approach to Dynamic Behavioral Modeling in Education
-
-
[1] Research Assistant, EdTech Research Association (ERA) headquarters, located at 15205 East North Lane, Scottsdale, Arizona, USA
-
- Localización: LatIA, ISSN-e 3046-403X, Nº. 3, 2025 (Ejemplar dedicado a: LatIA)
- Idioma: inglés
- Enlaces
-
Resumen
This study investigates the efficacy of integrating the Spectrum of Individuality Theory (SIT)—a dynamic, neuroplasticity-informed framework—into artificial intelligence (AI) systems for adaptive learning. Traditional AI models, rooted in static personality frameworks like the Five-Factor Model (FFM), often fail to capture real-time behavioral variability, limiting their adaptability. In a mixed-methods experiment, 120 undergraduate students were stratified into SIT-driven (n=60) and FFM-based (n=60) AI learning groups. The SIT system utilized real-time EEG and eye-tracking data to adjust content delivery, while the FFM system relied on fixed trait categorizations. Results demonstrated that the SIT group outperformed the FFM group in cognitive retention (mean post-test scores: 25.3 vs. 22.7; p < 0.01, Cohen’s d = 0.86) and exhibited progressive engagement improvements (Session 8 UES: 4.30 vs. 3.70; p < 0.001). Neurophysiological data revealed reduced stress biomarkers (theta/beta ratios: 3.15 vs. 3.75; p < 0.001), correlating with enhanced emotional regulation. However, ethical concerns, particularly data privacy (SIT: 4.10 vs. FFM: 3.20; d = 0.98), were heightened in the SIT group. These findings validate SIT’s potential to advance context-aware AI but underscore ethical risks tied to granular behavioral tracking. The study bridges psychological theory with AI design, advocating for interdisciplinary collaboration to balance adaptability with responsible innovation.
