中南大学学报（自然科学版）2018，Vol.49Issue(5)：1135-1140,6.DOI:10.11817/j.issn.1672-7207.2018.05.015
基于深度学习的多维特征微博情感分析
Analysis of Weibo sentiment with multi-dimensional features based on deep learning
摘要
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.关键词
情感分析/卷积神经网络/微博短文本/表情字符Key words
sentiment analysis/convolutional neural networks/Weibo short text/emoticons分类
信息技术与安全科学引用本文复制引用
金志刚,胡博宏,张瑞..基于深度学习的多维特征微博情感分析[J].中南大学学报（自然科学版）,2018,49(5):1135-1140,6.基金项目
国家自然科学基金资助项目(61571318) （61571318）
青海省科技项目(2015-ZJ-904) （2015-ZJ-904）
海南省科技项目(ZDYF2016153)(Project(61571318)supported by the National Natural Science Foundation of China （ZDYF2016153）
Project(2015-ZJ-904)supported by the Science Foundation of Qinghai Province （2015-ZJ-904）
Project(ZDYF2016153)supported by the Science Foundation of Hainan Province) （ZDYF2016153）
