摘要
为了保障疫情防控期间高职大学生心理调查项目统计结果的可靠性,文章提出了一种基于K-means聚类算法的学生心理压力分组方法。该方法综合利用了心理压力在生理、情绪、认知、行为等方面的外在表现数据,克服问卷调查中因主观性导致的学生自评压力数据失真的问题。通过对自评和聚类分组结果的对比分析,本研究证明了该方法的有效性。
In order to ensure the reliability of the statistical results of the psychological survey of vocational college students in COVID-19,this paper proposes a grouping method of students’psychological stress based on K-means clustering algorithm.This method makes comprehensive use of the external performance data of psychological stress in physiology,emotion,cognition,behavior and other aspects to overcome the problem of the distortion of students’self-evaluation pressure data caused by subjectivity in the questionnaire survey.The effectiveness of this method has been demonstrated through comparative analysis of self-assessment and clustering grouping results.
作者
许新刚
赵燕
Xu Xingang;Zhao Yan(School of Information Engineering,Xuzhou College of Industrial Technology,Xuzhou 221140,China)
出处
《无线互联科技》
2023年第19期95-100,共6页
Wireless Internet Technology
基金
江苏高校哲学社会科学研究项目
项目名称:重大疫情下高职大学生心理应激反应与干预对策研究
项目编号:2020SJA1130。江苏省教育科学“十四五”规划立项课题
项目名称:基于大数据的高职学生心理危机预警研究
项目编号:D202103129。
关键词
心理调查
描述性分析
数据挖掘
聚类算法
psychological investigation
descriptive analysis
data mining
clustering algorithm
