面向医院网络舆情分析的情感文本挖掘

Sentimental Text Mining for Hospital Network Public Opinion Analysis

随着互联网的迅速发展,人们可以在社交媒体平台表达和分享关于医患关系和医疗事故争议的想法。因此通过收集相关网络数据,使用情感分析或观点探索的数据挖掘技术来提取和分析客户的观点和情感对正确引导公众舆论、维护医院形象具有重要现实意义。提出一种基于情感特征的文本挖掘方法,该方法基于附加特征方法来提高准确性并减少实现时间,并使用奇异值分解和主成分分析来减少需要计算的数据量。这项研究有四个贡献:(1)提出了用于情感分类的数据预处理算法;(2)通过附加特征增强情感分类的准确性;(3)应用数据的奇异值分解和主成分分析实现数据降维;(4)设计基于不同功能的五个模块(有无词干)以比较分类性能。实验结果表明,该方法比其他方法具有更好的分类精度,并且可以减少分类算法的计算时间。

Due to rapid development of the Internet,people can express and share ideas about doctor-patient relationships and medical malpractice disputes on social media platforms.Therefore,by collecting relevant network data,using data analysis technology of sentiment analysis or viewpoint exploration,we can extract and analyze customer’s viewpoints and emotions,and it has important practical significance for correctly guiding public opinion and maintaining hospital image.This paper proposes a text mining method based on sentiment features,and based on additional feature methods to improve accuracy and reduce implementation time,and uses singular value decomposition and principal component analysis to reduce the amount of data that needs to be calculated.This research has four contributions:(1)proposing data preprocessing algorithms for sentiment classification;(2)enhancing accuracy of sentiment classification through additional features;(3)using singular value decomposition and principal component analysis to complete data dimensionality reduction;(4)designing five modules based on different functions(with or without stems)to compare classification performance.The experimental results show that the proposed method has better classification accuracy than other methods and can reduce the computation time of the classification algorithm.