| dc.description.abstract | Academic procrastination is a common problem in education, affecting student perfor mance and success. While traditional methods of studying procrastination frequently
rely on self-reports and surveys, recent advancements in Artificial Intelligence (AI)
provide novel possibilities for predicting and addressing procrastination behaviors.
However, the literature lacks a comprehensive understanding of AI’s role in predicting
academic procrastination. This review paper fills this gap by investigating the use of AI
techniques such as machine learning and deep learning algorithms to predict academic
procrastination. Using the PRISMA framework, the review summarizes findings from
various studies that use AI to analyze factors such as student demographics, online
learning behaviors, and academic performance metrics. The methodology entailed
screening and selecting studies based on criteria such as the use of AI in educational
settings and the emphasis on predicting procrastination. Procrastination is influenced
by age, gender, entry grades, and submission patterns, as well as challenges such as
data privacy, algorithmic bias, and variability across educational settings. For example,
biases in training data can result in unrelated predictions for specific demographics,
and ethical considerations are essential for responsible AI integration. The review
discovered that AI techniques can accurately identify at-risk students, allowing for
preventive measures that improve academic outcomes. It also highlights the importance
of ethical considerations and tailored AI models that account for contextual differences.
The findings show AI’s transformative potential in education, providing actionable
insights for reducing procrastination and fostering student success. | en_US |
