Psychological health is an important issue faced by college students, therefore conducting relevant research is meaningful. The use of Adaboost algorithm for ensemble learning, combined with the application of decision tree algorithm, can fully utilize the information in mental health test data and improve the prediction accuracy of the classifier. The C4.5 decision tree algorithm is a commonly used classification algorithm that can classify and distinguish samples based on feature attributes, so it has been selected as the basic algorithm for this study. In order to verify the effectiveness of this method, we selected the mental health test data of 2780 students from a certain university in 2020 for the experiment. Through analyzing experimental results, we found that the method can accurately identify sensitive psychological problems among students. In practical applications, this method can serve as an auxiliary tool to help schools accurately understand the distribution of students’ mental health problems, and thus develop corresponding educational measures and intervention plans. In summary, the mental health prediction method based on Adaboost algorithm proposed in the article, combined with the application of decision tree algorithm, can effectively identify psychological problems among college students. In the experiment, this method demonstrated high accuracy and robustness.