The effects of AI-guided individualized language learning: A meta-analysis
Han-Sol Lee, Jang Ho Lee
Abstract
Artificial intelligence (AI) has considerably advanced the methods for individualizing language learning opportunities, such as assessing learning progress and recommending effective individual instruction. In the present study, we conducted a meta-analysis to synthesize recent empirical findings pertaining to the utilization of AI-guided language learning and collected 61 samples (N = 8,282) from 17 research projects (e.g., Assessment to Instruction [A2i], Duolingo, and Project LISTEN). The results of our meta-analysis confirmed that AI-guided individualized language learning was effective for learners’ language development (d = 1.18, based on 26 within-group samples, N = 2,262) and had an overall positive treatment effect compared to business-as-usual conditions (d = 0.39, based on 35 between-group samples, N = 6,020). Moreover, the results of our moderator analyses for the treatment effect revealed that AI-guided language learning with machine learning and hybrid systems were more impactful than those with rule-based systems, which may be more helpful (compared to the former) in understanding how predictions are made from a pedagogical perspective. Evidence-based implications are provided based on the results of this meta-analysis.