Improving English semantic learning outcomes through AI chatbot-based ARCS approach

Comprehending abstract ideas in English semantics courses challenges English as a Foreign Language (EFL) learners. Teacher-centered methods fail to engage learners, decreasing motivation and contextual understanding. While the ARCS (Attention, Relevance, Confidence, Satisfaction) model emphasizes motivation, the conventional ARCS (C-ARCS) approach lacks interactivity. To address these limitations, this study proposed an AI chatbot-based ARCS (AIC-ARCS) approach to enhance interaction in English semantics learning. The AIC-ARCS approach integrates annotation and learner explanations of semantic concepts to an AI chatbot. A pre-test-post-test quasi-experimental design evaluated this approach. Fifty English-major undergraduates participated: twenty-five students used the AIC-ARCS approach, while twenty-five employed C-ARCS with peer discussions. Results showed the AIC-ARCS approach significantly improved semantic achievement and self-efficacy while reducing learning anxiety compared to C-ARCS. These findings suggest AI chatbots in ARCS-based frameworks create more engaging learning environments. This study highlights the potential of AI chatbot-enhanced pedagogies in transforming EFL instruction, particularly in English semantics. Future research should explore broader applications of AI chatbots and their long-term impact on learning.