AI−driven listening systems in language acquisition redefining auditory cognition in the intelligent era

This study addresses a critical gap in second language acquisition (SLA) research: the lack of integration between implicit comprehensible input and explicit metacognitive strategy training in AI-driven EFL listening instruction. With a mixed-methods design, it conducted a 16-week randomized controlled trial (RCT) with 120 Chinese EFL undergraduates (Mage = 19.2, CEFR A2-B1), comparing an AI-driven listening system (experimental group, n = 60) with traditional classroom instruction (control group, n = 60). The AI operationalized three core SLA frameworks: (1) Vygotsky’s Zone of Proximal Development (ZPD) via dynamically fading strategy prompts; (2) Nation’s affective filter hypothesis through real-time anxiety monitoring (heart rate sensors) and culturally familiar content curation; (3) Richards’metacognitive framework via context-specific prompts for prediction, inference, and summarization. Key findings: (1) The experimental group’s post-test listening scores were 11.2 points higher (M = 79.5 vs. 68.3, d = 1.02, p < 0.001); (2) Their FLCAS anxiety dropped 5.2 points (M = 24.5 vs. control M = 29.7, d=-1.05, p < 0.001); (3) Their top-down strategy use doubled (3.5→7.1 weekly uses), vs. a 10% increase in the control group.These findings suggest AI may modulate auditory cognition by synergizing implicit affective support and explicit scaffolding, challenging the input-strategy dichotomy. It advances SLA theory with empirical evidence for a tech-mediated framework, informing scalable, personalized EFL listening instruction.