高级检索|图表检索

图书情报工作 ›› 2019, Vol. 63 ›› Issue (18): 99-108.DOI: 10.13266/j.issn.0252-3116.2019.18.012

• 知识组织 • 上一篇    下一篇

基于字词向量的多尺度卷积神经网络微博评论的情感分类模型及实验研究

张柳1, 王晰巍1,2, 黄博3, 刘宇桐1   

  1. 1. 吉林大学管理学院 长春 130022;
    2. 吉林大学大数据管理研究中心 长春 130022;
    3. 吉林大学计算机科学与技术学院 长春 130022
  • 收稿日期:2018-12-15 修回日期:2019-02-23 出版日期:2019-09-20 发布日期:2019-09-20
  • 作者简介:张柳(ORCID:0000-0001-8688-4959),博士研究生,E-mail:598837913@qq.com;王晰巍(ORCID:0000-0002-5850-0126),副院长,教授,博士生导师;黄博(ORCID:0000-0001-9128-4659),博士研究生;刘宇彤(ORCID:0000-0003-3320-7369),硕士研究生。
  • 基金资助:
    本文系国家自然科学面上项目"信息生态视角下新媒体信息消费行为机理及服务模式创新研究"（项目编号：71673108）研究成果之一。

A Sentiment Classification Model and Experimental Study of Microblog Commentary Based on Multivariate Convolutional Neural Networks Based on Word Vector

Zhang Liu1, Wang Xiwei1,2, Huang Bo3, Liu Yutong1   

  1. 1. School of Management, Jilin University, Changchun 130022;
    2. Research Center for Big Data Management, Jilin University, Changchun 130022;
    3. School of Computer Science and Technology, Jilin University, Changchun 130022
  • Received:2018-12-15 Revised:2019-02-23 Online:2019-09-20 Published:2019-09-20

PDF

摘要： [目的/意义]微博评论情感分类模型可以为相关舆情监管部门正确管控话题事件的发展状况和舆情提供一定的指导作用。[方法/过程]基于字词向量的多尺度卷积神经网络，运用多尺度卷积核改善微博评论中上下文信息有限的条件制约，构建基于字词向量的多尺度卷积神经网络微博评论情感分类模型；通过爬取"微博热搜整改"数据，对模型的可行性和优越性进行验证。[结果/结论]验证结果表明基于字词向量的多尺度卷积神经网络在微博舆情等上下文信息有限的短文本分类任务中表现良好。本文在理论层面为微博舆情情感分类提供了更为准确的情感分类理论模型及分类方法，在实践层面可以更好地指导舆情监管部门对舆情的情感倾向进行更好的引导和监管。

关键词: 卷积神经网络, 字词向量, 多尺度卷积核, 微博评论, 情感分类

Abstract: [Purpose/significance] The microblog commentary sentiment classification model can play a guiding role for the relevant public opinion supervision departments to correctly control the development of the topic events and the public opinion.[Method/process] Based on the multi-scale convolutional neural network of word vector, this paper used multi-scale convolution kernel to improve the conditional constraints of finite context information in microblog commentary, and constructed multi-scale convolutional neural network microblog commentary emotion classification model based on word vector. Finally, the feasibility and superiority of the model were verified by crawling the real data of "microblogging hot search and rectification".[Result/conclusion] Verification results show that the multi-scale convolutional neural network based on word vector performs well in the short text classification task with limited context information such as weibo public opinion. On the theoretical level, this paper provides a more accurate emotional classification theory model and classification method for microblogging public opinion emotion classification. In practice, it can better guide the public opinion supervision department to better guide and supervise the emotional sentiment of public opinion.

Key words: convolution neural network, word vector, multiscale convolution kernel, Weibo comments, sentiment classification

中图分类号: