Engaging MOOC Students With Social-Emotional Support by Using Conversational Artificial Intelligence With Deep Learning (Poster 3)

• In Event: AERA Poster Session 12
  In Poster Session: Instructional Technology SIG Poster Session 2 (San Diego)

Abstract

This research aims to examine the extent to which the deep-learning-based conversational AI (ConvAI) models can offer responses similar to human-generated responses to the learners in MOOC forums. Specifically, under the framework of social support theory, this study has examined the use of state-of-the-art deep learning models recurrent neural network (RNN) and generative pretrained transformer 2 (GPT-2) to provide students with social-emotional support on discussion forums. We examined the ConvAI models both quantitatively and qualitatively, followed by a user survey to collect students’ opinions on the auto-generated responses. The results show that ConvAI could provide supportive and contextual replies to a similar extent compared to humans.

Authors

• Chenglu Li, University of Utah

• Wanli Xing, University of Florida