Using Adaptive Empathetic Responses for Teaching English

TL;DR

This paper introduces a novel spoken English-teaching chatbot that detects negative emotions via audio to provide adaptive, empathetic feedback, aiming to enhance learner engagement and reduce anxiety.

Contribution

It presents the first spoken English-teaching chatbot with integrated emotion detection and adaptive empathetic responses, utilizing automatic prompt optimization of ChatGPT.

Findings

Effective emotion detection from audio signals.

Improved learner engagement with empathetic feedback.

Positive preliminary user study results.

Abstract

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.