Speakers: Mehmet Arif Demirtas and Yoshee Jain
Title: PLAID: Supporting Computing Instructors to Identify Domain-Specific Programming Plans at Scale
Abstract: Pedagogical approaches focusing on stereotypical code solutions, known as programming plans, can increase problem-solving ability and motivate diverse learners. However, plan-focused pedagogies are rarely used beyond introductory programming. Our formative study (N=10 educators) showed that identifying plans is a tedious process. To advance plan-focused pedagogies in application-focused domains, we created an LLM-powered pipeline that automates the effortful parts of educators’ plan identification process by providing use-case-driven program examples and candidate plans. In design workshops (N=7 educators), we identified design goals to maximize instructors’ efficiency in plan identification by optimizing interaction with this LLM-generated content. Our resulting tool, PLAID, enables instructors to access a corpus of relevant programs to inspire plan identification, compare code snippets to assist plan refinement, and facilitates them in structuring code snippets into plans. We evaluated PLAID in a within-subjects user study (N=12 educators) and found that PLAID led to lower cognitive demand and increased productivity compared to the state-of-the-art. Educators found PLAID beneficial for generating instructional material. Thus, our findings suggest that human-in-the-loop approaches hold promise for supporting plan-focused pedagogies at scale.
Bios:
Mehmet Arif Demirtas (he/him) is a PhD student in the Siebel School of Computing and Data Science at UIUC, advised by Dr Katie Cunningham. Arif is interested in improving computer science education by modeling student learning through data-driven methods, supporting instructors in creating educational material for diverse domains, and developing learning environments for non-CS majors.
Yoshee Jain (she/her) is a junior in Computer Science at UIUC, working with Dr. Katie Cunningham. Yoshee is interested in developing AI-driven, human-in-the-loop systems to support instructors, enhance learner experiences, and bridge the gap between computing and other fields by making it more accessible and applicable across diverse domains.