Sun Xiaocong
School of Education Science, Xinxiang University, Xinxiang, China.
Front Psychol. 2022 Aug 11;13:974576. doi: 10.3389/fpsyg.2022.974576. eCollection 2022.
In order to improve education and teaching methods and meet the "heart" needs of college students in the era of big data, this paper analyzes the application of data mining technology in college mental health education, and introduces database technology and decision tree algorithm to support college mental health work. This process verifies the feasibility of this kind of system with the help of an example. Using the test standards outlined in this document, 1.5 previous test tasks were completed within the timeframe. During the system test, the error rate was 14% and the number of tests was 7%.However, the error rate in the development stage is 11%, which is lower than 19% of the old version. The error rate in the acceptance stage is 14%, which is lower than 5% of the old version. That is to say, most of the errors were found in time in the system analysis and design stage. 14% of the problems found in the development stage are basically small problems in the interface display, which do not need major changes. However, the old version also includes design defects found in the development stage, and only large-scale rewriting of the involved modules. In the research process, the work of mental health in Colleges and universities has been promoted. At this time, the law of psychological changes of college students has been summarized. Therefore, the support of data mining technology can better meet the needs of mental health education in Colleges and universities.
为了改进教育教学方法，满足大数据时代大学生的“心”需求，本文分析了数据挖掘技术在高校心理健康教育中的应用，并引入数据库技术和决策树算法来支持高校心理健康工作。此过程借助实例验证了这种系统的可行性。按照本文档概述的测试标准，在规定时间内完成了1.5个先前的测试任务。在系统测试期间，错误率为14%，测试次数为7%。然而，开发阶段的错误率为11%，低于旧版本的19%。验收阶段的错误率为14%，低于旧版本的5%。也就是说，大部分错误在系统分析和设计阶段被及时发现。在开发阶段发现的14%的问题基本都是界面显示方面的小问题，无需重大更改。而旧版本在开发阶段还存在设计缺陷，只能对涉及的模块进行大规模重写。在研究过程中，推动了高校心理健康工作。此时，总结出了大学生心理变化规律。因此，数据挖掘技术的支持能够更好地满足高校心理健康教育的需求。
