作　　者： ; (杨善林）;

机构地区： 合肥工业大学管理学院

出　　处： 《计算机科学》 2013年第11A期274-277,共4页

摘　　要： 网络商品评论情感分析对网络购物用户的决策有着重要的帮助,因此,分类准确性的提高一直是网络商品评论情感分析研究关注的重点问题之一。近些年,集成学习理论是提高分类精度的一种有效途径,并已有研究将Bagging、Boosting引入网络商品评论的情感分析领域,但对于Random Subspace集成学习方法关注相对较少。为此,本研究根据网络商品评论情感分析问题的高维度数据特征,提出一个新的网络商品评论情感分析方法 RS-SVM。该方法以集成学习中的Random Subspace为基础,选取目前在情感分析领域广泛应用的SVM作为基学习器,通过集成Random Subspace较强的学习能力,进一步提高网络用户评论情感分析的准确程度。最后,在网络商品评论情感分析经典数据库Movie Reviews上进行了实验,结果表明RS-SVM取得了比其它分类器都好的实验结果。 Abstract As product reviews in the interact are helpful for the decision of online shopping, and the classification accu- racy of sentiment analysis is one of important problems. Recently, ensemble learning has been proved to be an effective method of enhancing the classification accuracy. Bagging and Boosting have been applied into the sentiment analysis, while Random Subspace is paid less attention to. In this paper, an new method, RS-SVM, was proposed for sentiment analysis based on the characteristic of high dimension of product reviews dataset. RS^SVM uses the state-obthe-art SVM as base learner and Random Subspace as ensemble method in order to enhance the accuracy of sentiment analysis. Lastly, experiments based on movie reviewg dataset were conducted to verify the effectiveness of RS-SVM. Experimental results reveal that RS-SVM gets the best classification results compared with other methods.

关 键 词： 情感分析 商品评论 集成学习

领　　域： [自动化与计算机技术] [自动化与计算机技术]