Early Signs as Effective Indicators of Long-term Procrastination Using Machine Learning


  • AANIKA TANGIRALA The Lakeside School, Seattle, WA
  • AADHITYA RAMESH Thomas Jefferson High School for Science and Technology, Alexandria, VA
  • Mihai Boicu Information Sciences Technology, George Mason University, Fairfax, VA




Procrastination is a widespread issue that has a detrimental impact on one’s academic life and mental health. Thus, it is important to identify early signs in students that correlate with a greater risk of procrastination. Most early-detection procrastination research focuses on the analysis of student activity and interaction with course material to anticipate procrastination. However, the analysis of student-specific traits, such as personality, time perspective, and learning approach, in relation to procrastination habits is less studied. Some previous studies have analyzed the relationship between procrastination and factors such as a student’s personality, self-regulation, and general life satisfaction. These reports used survey data collection both to detect these early signs in participants and to measure procrastination. A variety of Machine Learning techniques were used to analyze this data, including correlational and regression analysis, neural networks, and linear support vector machines. This research found relationships such as procrastination being positively related to neuroticism and significantly predicted by poor time management, self-doubt, and irrational studying beliefs. An experiment will be developed to collect survey data for each of the student-specific traits and student activity data for measuring procrastination; ML models will analyze and explore relationships between these early signs and long-term procrastination.





College of Engineering and Computing: Department of Information Sciences and Technology