Enhancing Vocabulary Retention in EFL Learning: The Role of Generative AI Chatbots with Metacognitive Scaffolding

• In Event: AERA Roundtable Session Friday 7:45 am - Gold 4
  In Roundtable Session: AI as a Literacy Partner

Abstract

English vocabulary learning with generative Artificial Intelligence (AI) may not be effective if students are not equipped with sufficient metacognitive skills. This study proposed a pedagogical framework based on situated-learning theory (SLT) and self -regulated learning (SRL) theories for generative AI supported English as a foreign language (EFL) vocabulary learning. A quasi-experimental design was adopted, involving 296 seventh-grade students randomly assigned to three groups (AI-only, AI+Meta, and the Control groups). Results showed that the AI interventions enhanced self-monitoring skills but not for planning and evaluations skills and reduced disparities in receptive vocabulary acquisition, while metacognitive scaffolding significantly improved long-term productive vocabulary retention. The findings highlighted the potential of integrating metacognitive support into AI-assisted language learning to optimize vocabulary outcomes.

Authors

• Nanzhu Zhang, Beijing Normal University

• Linyi Yong, Beijing Normal University

• Yu Zhu, Beijing Normal University

• Siqi Li, Beijing Normal University

• Yi Zhang, Beijing Normal University

• Peidi Gu, Beijing Normal University

• Shuai Zhang, Anhui Normal University