自然科学版 英文版
自然科学版 英文版
自然科学版 英文版

您目前所在的位置:首页 - 期刊简介 - 详细页面

中南大学学报(自然科学版)

Journal of Central South University

第49卷    第5期    总第285期    2018年5月

[PDF全文下载]    [Flash在线阅读]

    

文章编号:1672-7207(2018)05-1135-06
基于深度学习的多维特征微博情感分析
金志刚1,胡博宏1, 2,张瑞1

(1. 天津大学 电气自动化与信息工程学院,天津,300072; 2. 天津大学 国际工程师学院,天津,300072)

摘 要: 提出1种基于卷积神经网络的多维特征微博情感分析新机制;利用词向量计算文本的语义特征,结合基于表情字符的情感特征,利用卷积神经网络挖掘特征集合与情感标签间的深层次关联,训练情感分类器;结合微博文本的语义和情感特征,同时利用卷积神经网络的抽象特征提取能力,进而改善情感分析性能。研究结果表明:引入表情字符的情感特征模型可使情感分析准确率提高2.62%;相比基于词典的机器学习模型,新机制将情感分析准确率与F度量分别提升21.29%和19.20%。

 

关键字: 情感分析;卷积神经网络;微博短文本;表情字符

Analysis of Weibo sentiment with multi-dimensional features based on deep learning
JIN Zhigang1, HU Bohong1, 2, ZHANG Rui1

1. School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China; 2. Tianjin International Engineering Institute, Tianjin University, Tianjin 300072, China

Abstract:A new mechanism of Weibo sentiment analysis based on convolutional neural networks with multi- dimensional features was proposed. The proposed mechanism combines semantic features from word vectors with sentiment features from emoticons, in which convolutional neural networks was used to mine deep correlation between features and labels. The performance of Weibo sentiment analysis was improved through mining multi-dimensional features and utilizing abstract features extraction ability of convolutional neural networks. The results show that the accuracy of sentiment analysis model based on emoticons increases by 2.62%. The accuracy and F measure increase by 21.29% and 19.20% respectively compared with that of machine learning model based on lexicon.

 

Key words: sentiment analysis; convolutional neural networks; Weibo short text; emoticons

中南大学学报(自然科学版)
  ISSN 1672-7207
CN 43-1426/N
ZDXZAC
中南大学学报(英文版)
  ISSN 2095-2899
CN 43-1516/TB
JCSTFT
版权所有:《中南大学学报(自然科学版、英文版)》编辑部
地 址:湖南省长沙市中南大学 邮编: 410083
电 话: 0731-88879765(中) 88836963(英) 传真: 0731-88877727
电子邮箱:zngdxb@csu.edu.cn 湘ICP备09001153号