This study aimed to develop task-based AI chatbots for primary English that prevent task interruptions based on a dialogue management algorithm. The participants were 18 students from an elementary school located in Seoul. The results were as follows. Firstly, two strategies for dialogue management were determined by referring to previous research: negotiation of meaning and context management. Dialogflow API was used to build the AI chatbots applying the algorithm. Entity, Prompts, and Context, among the API’s various functions, were mainly used to implement the dialogue management algorithm. Secondly, the discourse transcript between the chatbots and learners was analyzed according to the two strategies. Above all, the negotiation of meaning strategy was implemented well to prevent the interruption of communication by providing different prompts, including corrective feedback. Next, the context management strategy was also activated properly to resolve dialogue breaks by providing scaffoldings and transforming topics. However, some recognition errors occurred during the communication due to the chatbots’ incomplete recognition rate of Korean young language learners’ spoken English. Hence, there need to be in-depth studies on the measures to make up for these problems. Nevertheless, the current study may encourage further research on developing AI chatbots for various tasks by preventing task interruptions.
I. 서론
II. 이론적 배경
III. 연구 방법
IV. 연구 결과 및 논의
V. 결론 및 제언
참고문헌