面向产品评论细粒度情感分析.docVIP

面向产品评论细粒度情感分析 　　摘要：针对传统粗粒度情感分析忽略具体评价对象，以及现有细粒度情感分析方法忽略无关评价要素的问题，提出结合条件随机场（CRF）和语法树剪枝的方法对产品评论进行细粒度情感分析。采用基于MapReduce的并行化协同训练（Tritraining）的方法对语料进行半自主标注，利用融合多种语言特征的条件随机场模型，获取评论中的评价对象和正负面评价词。通过建立领域本体和句法路径库实现语法树剪枝，对含有多个评价对象和评价词的文本，去掉无关评价对象的干扰，抽取出正确的评价单元，最后形成可视化产品报告。实验结果显示，提出的方法在两种不同领域数据集上，识别情感要素的综合准确率达89%左右，情感评价单元的综合准确率也达89%左右。实验结果表明，与传统方法相比，结合CRF和语法树剪枝的方法识别准确率更高，性能更好。 　　关键词：产品评论；细粒度情感分析；MapReduce； 协同训练；条件随机场；语法树剪枝 　　Abstract： 　　The traditional sentiment analysis is coarsegrained and ignores the comment targets， the existing finegrained sentiment analysis ignores multitarget and multiopinion sentences. In order to solve these problems， a method of finegrained sentiment analysis based on Conditional Random Field （CRF） and syntax tree pruning was proposed. A parallel tritraining method based on MapReduce was used to label corpus autonomously. CRF model of integrating various features was used to extract positive/negative opinions and the target of opinions from comment sentences. To deal with the multitarget and multiopinion sentences， syntax tree pruning was employed through building domain ontology and syntactic path library to eliminate the irrelevant target of opinions and extract the correct appraisal expressions. Finally， a visual product attribute report was generated. After syntax tree pruning， the accuracy of the proposed method on sentiment elements and appraisal expression can reach 89% approximately.The experimental results on two product domains of mobile phone and camera show that the proposed method outperforms the traditional methods on both sentiment analysis accuracy and training performance. 　　英文关键词 　　Key words： 　　product comment； finegrained sentiment analysis； MapReduce； Tritraining； Conditional Random Field （CRF）； syntax tree pruning 　　0引言 　　随着Web2.0的盛行，人们表达情感和意见的方式已不再局限于传统的面谈、写日记等方式，而是逐渐转向网络平台，以文本的形式来表达。尤其体现在电子商务上，电子商务的发展，推动消费者网购热情的同时，也产生大量的产品评论。产品评论是消费者分享使用效果、评价商品的重要数据资源，为用户消费习惯的调查、企业制定营销策略和产品满意度调查等提供可靠的数据支持。人工浏览无法应对海量评论资源，如何方便快捷地挖掘出评论中有价值