中文摘要：

根据消费者在线评论,构建有向网络,从评论网络的拓扑性质出发建立在线评论情感倾向性分类模型。该模型首先以词语共现理论为基础构建评论的有向网络,然后挖掘网络中具有情感信息的子网络,将子网络中由程度词和否定词导致的情感偏移引入到韦伯-费希纳定律中,提出了一种新的在线评论情感相似性计算方法DNSA（Directed network and syntactic analysis）,利用该方法计算测试评论和训练中评论的相似度,选取相似度最大的K条评论的多数类作为该评论的类别。最后对酒店评论和手机评论进行实验,结果表明该模型可以有效的对评论作情感倾向性分类。

英文摘要：

The directed network is created for online reviews,and the model of emotional classification is proposed bynetwork topological properties. First,the directed network is built for online review based on co-occurrence theory,and thensub-network which has emotional information is mined, the Weber-Fechner Law is introduced for sub-network becauseof excursion caused by adverb and negative. A new approach called DNSA（Directed network and syntactic analysis） iscreated for calculating similarity of reviews based on above all. The similarity of review in test set and train set is computed,and the most of class as the class in the top K. At last, we conduct an experiment on hotel online reviews and mobile onlinereviews,the result indicates that our model can classify sentiment polarity of online review.