ABSTRACT
Participating in online communities has significant benefits to students learning in terms of students’ motivation, persistence, and learning outcomes. However, maintaining and supporting online learning communities is very challenging and requires tremendous work. Automatic support is desirable in this situation. The purpose of this work is to explore the use of deep learning algorithms for automatic text generation in providing emotional and community support for a massive online learning community, Scratch. Particularly, state-of-art deep learning language models GPT-2 and recurrent neural network (RNN) are trained using two million comments from the online learning community. We then conduct both a readability test and human evaluation on the automatically generated results for offering support to the online students. The results show that the GPT-2 language model can provide timely and human-written like replies in a style genuine to the data set and context for offering related support.
Acknowledgements
This work is partially supported by the National Science Foundation (NSF) of the United States under grant number 1901704. Any opinions, findings, and conclusions or recommendations expressed in this paper, however, are those of the authors and do not necessarily reflect the views of the NSF.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Notes on contributors
Hanxiang Du
Hanxiang Du is a PhD student in Educational Technology, College of Education at University of Florida. Her research interests are educational data analysis, learning analytics and STEM education.
Wanli Xing
Wanli Xing is an Assistant Professor of Educational Technology at University of Florida. His research interests are artificial intelligence, learning analytics, STEM education and online learning.
Bo Pei
Bo Pei received the BS and MS degree in Computer Science in 2011 and 2015, respectively. He is currently a doctoral student in the School of Teaching & Learning, College of Education, University of Florida. His research interests focus on online learning, educational data mining, especially applying the machine learning approaches into the educational settings to identify the different learning patterns from the learning behaviors and build models to analyze the associations between the learning patterns and final learning performances to help the instructors to provide individualized interventions for students.