Understanding the Role of Large Language Models in Personalizing and Scaffolding Strategies to Combat Academic Procrastination

Traditional interventions for academic procrastination often fail to capture nuanced, individual-specific factors. Large language models (LLMs) may address this gap by accepting open-ended inputs and customizing interventions to unique needs, yet user expectations and limitations remain underexplored. The authors conducted interviews and focus group discussions with 15 university students and 6 experts, using a technology probe that generated personalized advice for procrastination management. Findings highlight the need for structured, deadline-oriented steps, enhanced user support mechanisms, and adaptive questioning based on factors like busyness. The study provides design implications for LLM-based tools to manage procrastination while cautioning against their use for therapeutic guidance.

Ananya Bhattacharjee, Yuchen Zeng, Sarah Yi Xu, Dana Kulzhabayeva, Minyi Ma, Rachel Kornfield, Syed Ishtiaque Ahmed, Alex Mariakakis, Mary P Czerwinski, Anastasia Kuzminykh, Michael Liut, Joseph Jay Williams