基于人工智能的新时代大学生心理障碍预测研究

Research on Predicting Psychological Disorders of College Students in the New Era Based on Artificial Intelligence

心理障碍是影响新时代大学生的首要健康问题,目前尚无可用于筛查大学生心理障碍的早期预测工具。人工智能技术的迅速发展为心理健康领域的研究提供新的思路和方法。本研究基于浙江省不同层次高校在校生的样本数据资料,通过构建CNN-LSTM深度学习模型来识别大学生心理障碍的风险因素,并基于目标预测变量将CNN-LSTM与SVM、BP和CNN构建的模型进行比较,通过对比AUC等多个预测效果评价指标,最终验证构建的CNN-LSTM模型在大学生心理障碍预测上表现出最好的性能,且具有实际用于筛查大学生心理障碍的应用潜力。

Psychological disorders are the primary health issue affecting college students in the new era,and there is currently no early predictive tool available for screening psychological disorders among college students.The rapid development of artificial intelligence technology has provided new ideas and methods for research in the field of mental health.This study is based on sample data of students from different levels of universities in Zhejiang province.By constructing a CNN-LSTM deep learning model to identify risk factors for psychological disorders in college students,and comparing CNN-LSTM with models constructed by SVM,BP,and CNN based on target predictive variables,multiple predictive performance evaluation indicators such as AUC are compared.The final validation of the constructed CNN-LSTM model shows the best performance in predicting psychological disorders among college students,and has practical application potential for screening psychological disorders among college students.