Project A2I-MOOC: Artificially Intelligent and Interactive MOOCs

3 minute read

Published:

MOOCs have abysmal retention rates (5-15%) and high student failure rates (7-13%). In this project, we propose two ways to increase student engagement in MOOCs and other online courses through an artificially intelligent system that leverages machine learning and natural language processing. This system will (1) process, prioritize and organize students’ questions in real-time and provide the most relevant questions to instructors for answering during their live lectures, and (2) automate the creation of breakout rooms (which have recently become popular in Zoom classes) based on high-interest topics emerging from student questions and populated by like-minded students during live lectures.

Overview of Project A2I-MOOC

Today, online education is widely accepted, highly regarded, and completely necessary for educating a diverse and geographically distributed student population. Massive, Open, Online Courses (MOOCs), first introduced in 2008, have emerged as a popular approach to delivering distance education since 2012. The massive move to online education by educational institutions in early 2020 due to the COVID pandemic has further transformed teaching and learning for students and instructors. It is quite likely that these high levels of online education will continue even after normalcy is restored in society. Online courses, especially when there is a large teacher-to-student ratio, lead to significantly less opportunities for students to ask questions and have them answered by the teacher in real-time, and to discuss course topics among themselves during lectures. The flow of knowledge is often unidirectional, and students lack a supportive environment where they can learn from their peers. Instructors can quickly feel overwhelmed with many questions from large numbers of students, and due to the remote nature and geographically dispersed student body, students have very limited interactions with each other during live lectures. This can lead to student disengagement, and negatively affect learning. Not surprisingly, MOOCs have abysmal retention rates (5-15%) and high student failure rates (7-13%). Therefore, we propose two ways to increase student engagement in MOOCs and other online courses through an artificially intelligent system that leverages machine learning and natural language processing. This system will (1) process, prioritize and organize students’ questions in real-time and provide the most relevant questions to instructors for answering during their live lectures, and (2) automate the creation of breakout rooms (which have recently become popular in Zoom classes) based on high-interest topics emerging from student questions and populated by like-minded students during live lectures. A two-stage iterative design will be employed to ensure that a usable and effective system will be developed by the end of the project.

Image not Loading


Impact of Project A2I-MOOC

Online and remote learning, in the form of MOOCs or as part of K-16 education in general, is now a reality given the situation with COVID. This proposal addresses a key problem in this environment: the lack of opportunity for students to engage in the class and with their peers by asking questions (and having them answered) and participating in small-group discussions. Results from this project have the potential of impacting a large number of students who remotely take courses that still rely heavily on the traditional lecture format. The tool that we develop will work for courses on any subject matter, and will be made freely available to educational institutions across the country for use in any online course or MOOC, thereby potentially benefiting thousands of students. The project will enhance educational technology research in the EPSCoR state of Alabama, and provide graduate and undergraduate students at Auburn University in Alabama to conduct innovative research on artificial intelligence in education.