The development of listening and speaking skills in EFL via an artificially intelligent chatbot application: A quasi-experimental design study

Download
2024-1
Koç, Fatma Şeyma
This research aimed to explore the effects of using an artificial intelligence chatbot to enhance the listening and speaking skills of Turkish EFL learners. It was also intended to specify the experiences of language learners and strategies for using this tool and identify the characteristics of an ideal artificially intelligent chatbot for language learning. Quantitative and qualitative data were collected towards these aims using a quasi-experimental design. The quantitative data were collected through a quasi-experimental pre- and post-test control group design. The qualitative data were collected through reflective diaries, recordings of student-chatbot interaction, and semi-structured interviews. According to the findings, although there were significant differences within groups regarding pre-test and post-test speaking proficiency exam results, there were no significant differences between groups regarding listening and speaking post-test scores. The qualitative analysis also demonstrated that although learners faced various technical, pedagogic, and social constraints, there were also self-reports of enhanced language knowledge and skills. The interaction data analysis also showed that EFL learners adopted several interactional strategies to negotiate for meaning in the cases of conversational breakdowns. Based on the findings of this study, a framework for developing artificial intelligent chatbots for EFL learners was proposed. For this purpose, this study suggests a conceptual REPOST model, the guidelines for EFL teachers based on optimum AI chatbot qualities, and a teacher training component.
Citation Formats
F. Ş. Koç, “The development of listening and speaking skills in EFL via an artificially intelligent chatbot application: A quasi-experimental design study,” Ph.D. - Doctoral Program, Middle East Technical University, 2024.