基于大数据和机器学习的心理危机个体识别模型  

Individual identification model of psychological crisis based on big data and machine learning

作　　者：白树虎[1] BAI Shuhu(The Engineering&Technical College of Chengdu University of Technology,Leshan 614000,China)

机构地区：[1]成都理工大学工程技术学院,四川乐山614000

出　　处：《电子设计工程》2023年第13期17-21,共5页Electronic Design Engineering

基　　金：四川省教育厅2020年度高校心理健康教育研究课题(2020SXJP009)。

摘　　要：为了提升心理危机个体的识别效率,文中将大学生在社交媒体以及各类网络平台留下的数据文本信息作为研究对象,以自然语言处理的思路进行数学建模,引入了一种基于卷积运算的文本信息处理网络TCNN。该网络以Word2Vec词向量生成模型的输出为输入,可有效提取网络短文中的特征信息且生成特征向量。在综合分析了Word2Vec模型static与non-static训练方式的基础上,通过建立双通道的网络DTCNN提升了算法对文本局部敏感信息的提取效率。在自建数据集上进行仿真。结果表明,TCNN、DTCNN网络较传统的贝叶斯判别法,指标性能有了显著改善。其中,DTCNN模型的准确率、召回率及F1值分别提升了9.3%、4.5%及8.1%。此外,改进后的DTCNN网络较TCNN网络的F1值也得到了进一步提升。In order to improve the recognition efficiency of individuals in psychological crisis,this paper takes the data text information left by college students in social media and various network platforms as the research object,carries out mathematical modeling with the idea of natural language processing,and introduces a text information processing network based on convolution operation TCNN,which takes the output of Word2Vec word vector generation model as the input,and can effectively extract the feature information in network essays and generate feature vectors.Based on the comprehensive analysis of static and non-static training methods of Word2Vec model,the efficiency of the algorithm for extracting local sensitive information of text is improved by establishing a dual channel network DTCNN.The simulation results on the self built data set show that TCNN and DTCNN networks have significantly improved the index performance compared with the traditional Bayesian discriminant method,in which the accuracy,recall and F1 value of DTCNN model have increased by 9.3%,4.5% and 8.1% respectively.In addition,after the improvement of this paper,the F1 value of DTCNN network is also significantly higher than that of TCNN network.

关 键 词：大数据 机器学习 卷积网络 Word2Vec 自然语言处理 心理危机 

分 类 号：TN249[电子电信—物理电子学] TP212[自动化与计算机技术—检测技术与自动化装置]