中文摘要：

微博是互联网舆论演化的重要平台，对微博进行情感分析，有助于及时掌握社会热点和舆论动态。由于微博数据内容简短、特征稀疏、富含新词等特征，微博情感分类依然是一个较难的任务。传统的文本情感分类方法主要基于情感词典或者机器学习等，但这些方法存在数据稀疏的问题，而且忽略了词的语义、语序等信息。为了解决上述问题，提出一种基于卷积神经网络的中文微博情感分类模型CNNSC，实验表明相比目前的主流方法，CNNSC的准确率提高了3.4%。

英文摘要：

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.