计算机应用与软件2017，Vol.34Issue(4)：157-164,177,9.DOI:10.3969/j.issn.1000-386x.2017.04.027
基于卷积神经网络的中文微博情感分类
CHINESE MICRO-BLOG EMOTION CLASSIFICATION BASED ON CNN
摘要
Abstract
Microblogging is an important platform for the evolution of Internet media, microblogging emotional analysis, help to grasp the social hot spots and public opinion.As the content of Micro-blog short, sparse features, rich in new words and other features, Micro-blog emotional classification is still a difficult task.Traditional text emotion classification methods are mainly based on emotional dictionary or machine learning, but these methods have sparse data, and ignore the semantic, word order and other information.In order to solve the above problem, this paper proposes a Chinese microblogging emotion classification model based on CNN.The experiment shows that the accuracy of the model is improved by 3.4% compared with the current mainstream method.关键词
情感分类/卷积神经网络/微博分类Key words
Emotion classification/Convolutional neural network/Micro-blog classification分类
信息技术与安全科学引用本文复制引用
冯多,林政,付鹏,王伟平..基于卷积神经网络的中文微博情感分类[J].计算机应用与软件,2017,34(4):157-164,177,9.基金项目
国家自然科学基金项目(61502478) （61502478）
国家核高基项目(2013ZX01039-002-001-001) （2013ZX01039-002-001-001）
国家高技术研究发展计划项目(2013AA013204). （2013AA013204）
