How COVID-19 Affected Computer Science MOOC Learner Behavior and Achievements: A Demographic Study.

Learner data from multiple instances of two introductory Python MOOCs, offered before and during the COVID-19 pandemic, were analyzed to see if and how learner behavior and overall learning outcomes changed during the pandemic. We found a surge in interest during the pandemic, but the certification rate fell short of the pre-pandemic average. Moreover, this drop in certification rate is more noticeable for the advanced course in the sequence, and is more pronounced in groups traditionally underrepresented in computer-science and coding communities. Additionally, we analyzed learners' interaction with one another on the course discussion forum, and performed a sentiment analysis of the forum comments using natural language processing, which revealed behavioral trends that differed significantly during the pandemic.