Design principles and architecture of a second language learning chatbot

Abstract

The purpose of this article is to set out the design principles and architecture of a second language (L2) learning voice chatbot. Building on L2 acquisition theories and chatbot research, in this article, we report on a South Korean government-funded longitudinal project in which we designed and developed a chatbot called "Ellie". Chatbot Ellie has three chat modes, "General Chat," "Task Chat," and "Skills". In the General Chat mode, L2 users can have short talks about personal information, whereas in the Task Chat mode, they can engage in a wide range of problem-solving L2 tasks to achieve task goals by exchanging meanings with Ellie. The Skills mode offers form focusedlanguage practice. Ellie was piloted among 137 Korean high school students, who used Ellie individually or in a group, for seven weeks in their English classes. The quality of the chatbot was investigated in terms of the appropriateness of language level, continuity of conversation, and success in task performance. Based on the results of the pilot, Ellie appears to have considerable potential to become an effective language learning companion for L2 learners, and has implications for the design and developments of future L2 chatbots.