中文摘要：

该文研究有监督学习方法在多文档文本情感摘要中的应用.利用从亚马逊中文网和亚马逊英文网上收集的产品评论语料,抽取文本内特征、PageRank特征、情感特征和评论质量特征,基于有监督方法进行多文档文本情感摘要抽取.实验结果表明有监督学习方法比无监督学习方法在ROUGE值上有显著的提高,情感特征和评论质量特征均有助于文本情感摘要.

英文摘要：

This paper investigates the application of supervised learning methods in multi-document opinion summari- zation. We use the corpus collected from Amazon, extract text features, PageRank feature, opinion features and re- views quality features, and, finally, generate the multi-document opinion summarization based on supervised learn- ing method. Experimental results show that the ROUGE values are significantly improve by using supervised learn- ing method than that unsupervised learning method. The opinion features and reviews quality features are helpful for summarization.