Exploring learners’ well-being in AI-supported English learning from a self-determination theory perspective

Artificial intelligence (AI) is increasingly reshaping English learning, yet limited attention has been paid to how AI-supported learning environments are associated with learners’ well-being. Drawing on self-determination theory, this study examined the relationships among basic psychological needs, flow, self-efficacy, peace of mind, and well-being. A cross-sectional survey was conducted with 694 undergraduate students from universities in China who had used AI-enabled tools for English learning. Structural equation modelling (SEM) tested the hypothesized direct and mediating relationships, while artificial neural network (ANN) analysis identified the relative predictive importance of the antecedents of well-being. The SEM results showed that basic psychological needs were positively associated with well-being, flow, self-efficacy, and peace of mind. Flow, self-efficacy, and peace of mind were also positively associated with well-being and mediated the association between basic psychological needs and well-being. The ANN results indicated that self-efficacy was the most important predictor, followed by peace of mind, flow, and basic psychological needs. These findings suggest that learners’ well-being is shaped by motivational, experiential, cognitive, and affective mechanisms in AI-supported English learning.