| 基于网络评论语言学结构的情感倾向识别模型 |
| |
| 引用本文： | 张素智,樊得强,李宝燕.基于网络评论语言学结构的情感倾向识别模型[J].郑州大学学报(自然科学版),2011(1):80-84. |
| |
| 作者姓名： | 张素智 樊得强 李宝燕 |
| |
| 作者单位： | 郑州轻工业学院计算机与通信工程学院,河南郑州450002 |
| |
| 基金项目： | 河南省重点科技攻关项目 编号082102210054; 郑州市科技攻关项目 编号0910SGYG23259-3 |
| |
| 摘 要： | 展示了一种新的基于网络评论语言学结构的情感倾向识别模型,固定情感词元模型（fixed sentiment terms model）.该方法利用基于固定情感词元的3种特定搭配模式来构造识别算法,通过基于增量的tf-idf模型的相关用户反馈不断更新特征词元集合.通过与传统的情感识别方法相比较,此方法可以较为明显地提高情感分类的效率和准确率.
|
| 关 键 词： | 语言学结构 固定情感词元 增量的tf-idf模型 情感特征选择 情感分类器 |
Sentiment Polarity Recognition Model Based on Linguistic Structure of Network Reviews |
| |
| ZHANG Su-zhi,FAN De-qiang,LI Bao-yan.Sentiment Polarity Recognition Model Based on Linguistic Structure of Network Reviews[J].Journal of Zhengzhou University (Natural Science),2011(1):80-84. |
| |
| Authors: | ZHANG Su-zhi FAN De-qiang LI Bao-yan |
| |
| Institution: | (College of Computer and Communication Engineering,Zhengzhou University of Light Industry,Zhengzhou 450002,China) |
| |
| Abstract: | A new sentimental polarity recognition model based on linguistic structure of emotion states-fixed sentiment terms model was presented.The proposed method used three types of specific collocation pattern to construct the recognition algorithm based on fixed sentiment terms.These feature term sets were gradually updated by relevant feedbacks from the users which based on incremental tf-idf model.Comparison was between the traditional method and fixed sentimental terms model.All tests showed the proposed method got a higher efficiency and accuracy rate of the emotion classifier. |
| |
| Keywords: | linguistic structure fixed sentimental terms incremental tf-idf model sentimental feature extraction sentimental classifier |
| 本文献已被 维普 等数据库收录！ |
