Predictive analysis of college students' academic procrastination behavior based on a decision tree model

Predicting academic procrastination among college students in the context of a public crisis could provide essential academic support and decision-making strategies for higher education institutions to promote student psychological health. Notably, research focusing on predicting academic procrastination behavior among college students in the context of a global crisis is still limited. The purpose of this study is to address this gap by constructing a predictive model based on the decision tree algorithm to predict academic procrastination behavior among college students. A total of 776 college students from the Guangxi Zhuang Autonomous Region of China participated in this study. The study gathered data from multiple aspects relevant to academic procrastination behavior, including demographic information, academic achievements, subjective well-being, smartphone addiction, negative emotions, self-esteem, life autonomy, pro-environmental behavior, academic achievement, and sense of school belonging. Descriptive statistical analysis was conducted utilizing SPSS version 26.0, and decision tree model analysis was performed with Modeler 18.0. The findings of this study identified eight predictive factors of college students' academic procrastination in order of importance: subjective well-being, smartphone addiction, negative emotions, self-esteem, life autonomy, pro-environmental behavior, academic performance, and sense of school belonging. The model accuracy was 85.78%, and indicating a relatively high level of prediction. The findings of this study not only provided a new perspective for understanding academic procrastination but also offered practical guidance for educators on how to mitigate this behavior.