Effects of GenAI-empowered interactive support on university EFL students' self-regulated strategy use and engagement in reading

Reading poses challenges for learners of English as a foreign language (EFL), as it requires strategic engagement with the text through an interactive meaning-making process. Self-regulated learning (SRL) training, which helps learners develop the ability to make strategic efforts to manage their reading process and maintain engagement in reading, has been increasingly used to assist EFL learners. However, one limitation of existing SRL training is the lack of interactive personalised support tailored to the specific needs of individual students. Recent developments in generative artificial intelligence (GenAI) may help address this limitation. This study explores how interactive personalised SRL support via a GenAI chatbot might affect university EFL learners' self-regulated strategy use and engagement in reading. Sixty-one Chinese EFL students from two classes at a university received a 45-min training session on SRL in reading and then engaged in a 12-week self-directed reading using an online reading platform embedded with SRL support. One class (the experimental group, N = 31) had access to the chatbot on the platform to support their self-regulated reading, while the other class (the control group, N = 30) received no chatbot assistance on the platform. Self-regulated reading strategy use and reading engagement were assessed through pre- and post-questionnaires, log data on the platform, and semi-structured interviews. It was found that the intervention significantly improved students' self-regulated reading strategy use and reading engagement, indicating the positive effect of GenAI-enabled interactive personalised SRL support. This study substantiates the value of interactive SRL support in the context of EFL reading.