Exploring individual's emotional and autonomous learning profiles in AI-enhanced data-driven language learning: An expanded sor perspective
Honggang Liu, Jiqun Fan, Miaoyue Xia
Abstract
Artificial Intelligence (AI) technology has significantly empowered English as a Foreign Language (EFL) education, effectively addressed the individual needs of learners and advanced research into individual differences under Data-Driven Learning (DDL). Artificial Intelligence (AI) has not only transformed pedagogical approaches in EFL education but has also opened new avenues for Data-Driven Learning (DDL) research, particularly in examining learner individuality through advanced data analytics. In AI-enhanced DDL, studies examining learners' emotional profiles through data are notably rare, and the mechanisms by which emotional differences impact language skill development and academic achievement require further investigation. To address this gap, the current study focuses on 753 undergraduate non-English major students from three universities in East China. It investigates the mediating role of learners' autonomy and changes in learning attitudes on the pathways affecting academic engagement and continuance intention. The study extends the application of the SOR theory within AI-enhanced education, elucidating the psychological and emotional pathways through which external stimuli influence individual academic performance. Additionally, it provides insights into students' emotional regulation in AI-enhanced data-driven learning. Educational relevance and implications Data-Driven Learning (DDL) is an instructional approach that leverages large datasets, typically from corpora, to facilitate individualized language learning, which is also a significant direction for the application of AI in education. By leveraging AI technologies to analyze personal learning data, especially psychological and emotional data, learners can more efficiently plan their self-directed learning. The current study explores the important role of psychological and emotional factors in AI-enhanced DDL under the context of Artificial Intelligence in Education (AIED), drawing on the Stimulus-Organism-Response (S-O-R) theory and Self-Determination Theory (SDT). The findings of this study provide pedagogical insights for teachers in AIED contexts, enhance learners' individual regulatory capabilities during self-directed learning, and offer practical guidance for the development and optimization of AIED-related software.