The flipped classroom in computer science has become a popular pedagogy where students complete preparatory reading and videos before class, leaving class time for hands-on practice. In theory, students come to class predisposed with knowledge to complete programming tasks, quizzes, and homework assignments. However, if students do not complete or do not fully understand the preparatory material, those students will not be equipped for class and may also be embarrassed to ask questions during class. In this study, we created a gamified quiz that is powered by a Large Language Model (LLM) that loads in questions from the flipped content transcripts. The game offers students a fun assessment after completing the flipped content that will both motivate them and prepare them for class. The game also provides an anonymous way for students to ask questions as they progress through the game content. Those questions can then be analysed by the instructor and reviewed in class. The study compares in-class quiz scores of a control group versus a group that had access to the gamified quiz in an undergraduate software engineering course over three consecutive course modules. The results obtained from both quantitative and qualitative data are promising, showing an increase in student in-class quiz scores along with positive student engagement with the gamified quiz. Students also reported that the game made them more comfortable with asking questions. Future work would extend this research to more students and over a longer period. The LLM and gamification also have much potential, where games can be created dynamically and be customized and personalized for each student's needs. This work shows an exciting gap in research that could lead to gamified experiences for students in the flipped model that are both relevant and personalized with the use of a LLM, offering the students the greatest chance for success.
Read full abstract