Natural Language Generation Using Deep Learning to Support MOOC Learners

• Published in: International journal of artificial intelligence in education 2021-06, Vol.31 (2), p.186-214
• Main Authors: Li, Chenglu, Xing, Wanli
• Format: Article
• Language: English
• Subjects: AI4MOOCs: Artificial Intelligence; Algorithms; Artificial Intelligence; Automatic text analysis; Automation; Chatbots; Community support; Computer Mediated Communication; Computer Science; Computers and Education; Deep learning; Distance learning; Educational objectives; Educational Resources; Educational Technology; Feedback (Response); Language; Machine learning; modeling and assessment for MOOCs. A step beyond; Natural language; Natural Language Processing; Online Courses; Online instruction; Pedagogy; Reading Comprehension; Recurrent neural networks; sensoring; Social support; Speech recognition; Students; User Interfaces and Human Computer Interaction
• ISSN: 1560-4292; 1560-4306
• DOI: 10.1007/s40593-020-00235-x

Among all the learning resources within MOOCs such as video lectures and homework, the discussion forum stood out as a valuable platform for students’ learning through knowledge exchange. However, peer interactions on MOOC discussion forums are scarce. The lack of interactions among MOOC learners can yield negative effects on students’ learning, causing low participation and high dropout rate. This research aims to examine the extent to which the deep-learning-based natural language generation (NLG) 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 informational, emotional, and community support with NLG on discussion forums. We first trained an RNN and GPT-2 model with 13,850 entries of post-reply pairs. Quantitative evaluation on model performance was then conducted with word perplexity, readability, and coherence. The results showed that GPT-2 outperformed RNN on all measures. We then qualitatively compared the dimensions of support provided by humans and GPT-2, and the results suggested that the GPT-2 model can comparably provide emotional and community support to human learners with contextual replies. We further surveyed participants to find out if the collected data would align with our findings. The results showed GPT-2 model could provide supportive and contextual replies to a similar extent compared to humans.