期刊文献+

基于文本词性结构和PCA算法的问卷优化 被引量:1

Questionnaire Optimization Based on Text Part-of-Speech Structure and PCA Algorithm
原文传递
导出
摘要 为了更准确、更高效的对车型进行评价,帮助企业了解自身优劣势,因此本文对传统的调研问卷进行优化。首先本文采用正则表达式利用常见的标点符号对近一年来总结的文本数据进行断句、筛选出包含情感和态度的语句、对筛选后的语句根据汽车行业指标进行分词;然后利用词性标注方法对句子进行词性分析,得到句子的词性结构;其次再利用主成分分析法(PCA)对得到的词性结构中选择贡献度占比率最高的一组,利用此时的词性结构优化当前的问卷方法,从而可以更准确、更高效的对车型进行评价,帮助企业了解自身优劣势,实现精准营销。 In order to evaluate car models more accurately and efficiently and help enterprises understand their own advantages and disadvantages,this article optimizes the traditional questionnaire.First of all,this article uses regular expressions to use common punctuation marks to break the text data summarized in the past year,filter out sentences containing emotions and attitudes,and segment the filtered sentences according to the automotive industry indicators;then use the part-of-speech tagging method to Perform part-of-speech analysis on the sentence to get the part-of-speech structure of the sentence;secondly,use the principal component analysis(PCA)to obtain the part of the group with the highest contribution to the obtained part-of-speech structure,and use the part-of-speech structure at this time to optimize the current questionnaire method,so that More accurate and efficient evaluation of car models helps companies understand their own advantages and disadvantages and achieve precise marketing.
作者 杨靖 张帆 郭雅鑫 Yang Jing;Zhang Fan;Guo Yaxin(China Automotive Technology&Research Center Co.,Ltd.,Tianjin 300300)
出处 《中国汽车》 2020年第9期14-19,共6页 China Auto
关键词 词性标注 主成分分析法 词性结构 贡献度 part-of-speech tagging principal component analysis part-of-speech structure contribution
  • 相关文献

参考文献7

二级参考文献52

共引文献49

同被引文献12

引证文献1

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部