摘要
情感分类是一项具有较大实用价值的分类技术,它可以对网上纷繁复杂的信息进行情感倾向标注,为用户提供一个简洁的总结信息,进而为人们制定决策提供帮助,然而目前针对汉语的情感分类开展的工作并不多。提出一种基于SVM机器学习的情感分类方法,并引入基于2-POS模型的句子主观性分析方法,利用SVM进行机器学习,实现汉语评论的情感分类。实验表明这种方法能够有效地判定评论信息的情感倾向。
Sentiment classification is a technology with great practical value. It can be used to analyze and mine user＇s opinion on the Web, help people making decisions. However, there is not too much related work done for Chinese reviews. Presents a sentiment classification method for Chinese reviews based on SVM. And introduces a sentence subjectivity analysis method based on 2-POS model and uses SVM to classify the reviews into positive or negative. Experiment shows that our method can gain a well performance of sentiment classification for Chinese reviews.
出处
《现代计算机》
2012年第8期17-21,共5页
Modern Computer
