영어 상호작용 촉진을 위한 과업 기반 AI 챗봇 활용 및 학생 발화 분석

A study of using task-based artificial intelligence(AI) chatbot for further interaction in English and the analysis of students’ production.

This study aimed to explore the possibility of using artificial intelligence(AI) Chatbot in English class to facilitate communication. Participants were 19 students in 6 th grade and performed 3 interactive tasks with Google Dialogflow API Chatbot. Tasks were exchanging small talk(task1), information gap activity(task2), and solving problems(task3), adopted from elementary English textbooks. The conversations were transcribed by the history function of Dialogflow and analyzed quantitatively to examine the production of participants and the success rates of each task and discourse. Furthermore, quantitative and qualitative analyses were executed to investigate how the prompts, activated by Chatbot, work as negotiation of meaning and elicitation to proceed interaction. The results revealed that the average t-unit of participants’ production showed 10, and they tended to speak 3-4 words in conversation. Next, the success rates of discourse and task were different for each task. The rate of task1 and task2 showed more than 65% compared to the task3. Despite the rate, Chatbot’s prompts provided meaningful effect on developing communicative ability by leading continual talk. Eventually, this study gave suggestion for integrating AI Chatbot into classroom to provide affordances for students’ using English, and for future progress of AI Chatbots as tools in foreign language education.