English

Using Adaptive Empathetic Responses for Teaching English

Computation and Language 2024-04-23 v1

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.

Keywords

Cite

@article{arxiv.2404.13764,
  title  = {Using Adaptive Empathetic Responses for Teaching English},
  author = {Li Siyan and Teresa Shao and Zhou Yu and Julia Hirschberg},
  journal= {arXiv preprint arXiv:2404.13764},
  year   = {2024}
}

Comments

Accepted to BEA workshop at NAACL 2024

R2 v1 2026-06-28T16:01:33.063Z