AI-Enhanced Vocabulary Acquisition in Conflict-Affected Contexts: A Study of Yemeni EFL Learners’ Adaptations, Challenges, and Outcomes

Abstract

Artificial intelligence (AI) technologies have revolutionized language learning, offering personalized, adaptive, and interactive tools for enhancing vocabulary acquisition. However, implementing AI-driven solutions in conflict-affected regions like Yemen presents unique challenges, including infrastructural constraints, socioeconomic barriers, and the need for cultural relevance. This study explores the effectiveness and obstacles of AI-enhanced vocabulary learning among 75 Yemeni university-level English as a Foreign Language (EFL) students through a mixed-methods approach. The research examines learners’ engagement with AI vocabulary tools, socio-technical barriers impeding adoption, and the comparative effectiveness of AI-mediated versus traditional learning methods. The findings reveal a complex interplay between AI’s potential for improving retention, engagement, and confidence, and the systemic challenges of cost, internet access, and cultural alignment. While AI tools demonstrate promise, their full impact hinges on addressing these barriers through localized solutions, policy interventions, and hybrid models that balance innovation with accessibility. This study contributes to the discourse on AI in education by highlighting the importance of contextually grounded approaches that account for the socioeconomic realities of marginalized learning environments.