Liang Liang, Zheng Yong, Ge Qiluo, Zhang Fengrui
College of Sports Science, Changsha Normal University, Changsha, China.
Physical Education Institute, China West Normal University, Nanchong, China.
Front Psychol. 2022 Mar 3;12:762725. doi: 10.3389/fpsyg.2021.762725. eCollection 2021.
This study aims to explore new educational strategies suitable for the mental health education of college students. Big data and artificial intelligence (AI) are combined to evaluate the mental health education of college students in sports majors. First, the research status on the mental health education of college students is introduced. The internet of things (IoT) on mental health education, a structure based on big data and convolutional neural network (CNN), is constructed. Next, the survey design and questionnaire survey are carried out. Finally, the questionnaire data are analyzed and compared with the mental health status under traditional education. The results show that the CNN model has good accuracy and ability to distinguish symptoms, so it can be applied to the existing psychological work in colleges. In the symptom comparison survey, under the traditional education and big data network, the number of college students with mild mental health problems is found to be 158 (84.9%) and 170 (91.4%), respectively. It indicates that the number of college students with moderate mental health problems decreases significantly. In the comparative investigation of the severity of mental problems, the number of students with normal mental health, subhealth, and serious mental health problems under the background of traditional mental health education is 125 (67.2%), 56 (30.1%), and 5 (2.7%), respectively. The mental health status of college students under the influence of big data networks on mental health education is better than that of traditional mental health education. There are 140 students with normal mental health, a year-on-year increase of 16.7%. In the comparative survey of specific mental disorders, students with obsessive-compulsive symptoms under traditional mental health education account for 22.0% of the total sample, having the largest proportion. In the subhealth psychological group under the big data network on mental health education, the number of hostile students decreases by 7, which is the psychological factor with the most obvious improvement. Hence, the proposed path of mental health education is feasible.
本研究旨在探索适合大学生心理健康教育的新策略。将大数据与人工智能(AI)相结合,对体育专业大学生的心理健康教育进行评估。首先,介绍大学生心理健康教育的研究现状。构建基于大数据和卷积神经网络(CNN)的心理健康教育物联网结构。接下来,进行调查设计和问卷调查。最后,对问卷数据进行分析,并与传统教育下的心理健康状况进行比较。结果表明,CNN模型具有良好的准确性和症状辨别能力,因此可应用于高校现有的心理工作中。在症状比较调查中,发现在传统教育和大数据网络下,有轻度心理健康问题的大学生人数分别为158人(84.9%)和170人(91.4%)。这表明有中度心理健康问题的大学生人数显著减少。在心理问题严重程度的对比调查中,在传统心理健康教育背景下,心理健康正常、亚健康和严重心理健康问题的学生人数分别为125人(67.2%)、56人(30.1%)和5人(2.7%)。大数据网络对心理健康教育影响下的大学生心理健康状况优于传统心理健康教育。心理健康正常的学生有140人,同比增长16.7%。在特定精神障碍的对比调查中,传统心理健康教育下有强迫症状的学生占总样本的22.0%,占比最大。在心理健康教育大数据网络下的亚健康心理群体中,敌对学生人数减少了7人,是改善最明显的心理因素。因此,所提出的心理健康教育路径是可行的。