AI-Customized Digital Picture Books to Enhance Vocabulary Learning in Early ELT Classrooms: A Quasi-Experimental Study
Abstract
Artificial intelligence (AI) is increasingly shaping English language teaching by enabling personalized and multimodal instructional approaches. This study investigates the use of AI-customized digital picture books (DPBs) to enhance vocabulary learning in early primary classrooms. The novelty of this work lies in transforming prescribed textbook units into AI-generated, curriculum-aligned digital stories that integrate synchronized text, visuals, audio narration, and interactive features to support vocabulary acquisition. A five-week quasi-experimental design is implemented with 38 Grade 2 and Grade 3 learners following the NCERT curriculum. Vocabulary development is examined through pre- and post-assessment alongside classroom observations and teacher reflections. The findings indicate clear improvement in learners’ word recognition, contextual understanding, pronunciation, and sentence usage after engagement with AI-customized DPBs. Qualitative insights further show increased learner engagement, confidence, and active participation during multimodal reading sessions. The results demonstrate that carefully designed AI-supported digital materials, when integrated with teacher mediation, create cognitively supportive and socially interactive environments for vocabulary development. This study contributes to the growing field of AI-enhanced language education by presenting an empirically grounded model for integrating generative AI tools into early ELT practice