Using Adaptive Empathetic Responses for Teaching English
This addresses the problem of student engagement and anxiety in language learning, but it is incremental as it applies existing methods to a new domain.
The paper tackled the lack of explicit empathy in English-teaching chatbots by building the first spoken chatbot with adaptive, empathetic feedback, evaluated through a preliminary user study.
Existing English-teaching chatbots rarely incorporate empathy explicitly in their feedback, but empathetic feedback could help keep students engaged and reduce learner anxiety. Toward this end, we propose the task of negative emotion detection via audio, for recognizing empathetic feedback opportunities in language learning. We then build the first spoken English-teaching chatbot with adaptive, empathetic feedback. This feedback is synthesized through automatic prompt optimization of ChatGPT and is evaluated with English learners. We demonstrate the effectiveness of our system through a preliminary user study.