The use of Artificial Intelligence in English language assessment: Empirical evidence and future directions

Abstract

Artificial intelligence (AI) is increasingly recognised as a useful tool for assessment, but its specific role in English language assessment remains unexplored. We conducted a scoping review of peer-reviewed studies published between 2011 and 2025, following the framework by Arksey and O’Malley (2005). Results show seven main ways AI is used in English assessment: generating test items, using chatbots for conversation practice, marking and scoring, supporting self-assessment, enabling adaptive testing, giving instant feedback, and recognising speech. AI helps make assessments more efficient, keeps students engaged, and supports more personalised learning. We also found that AI is helping teachers develop flexible teaching practices, meet standards, and manage assessments more effectively. This review highlights both the potential and the challenges of using AI in English language assessment and calls for more research to support its responsible and effective use in schools.