[1]刘欢欢,李寿山,周国栋,等.中文情绪识别方法研究[J].江西师范大学学报(自然科学版),2013,(02):120-124.
 LIU Huan-huan,LI Shou-shan,ZHOU Guo-dong,et al.A Study on Chinese Emotion Recognition Method[J].,2013,(02):120-124.
点击复制

中文情绪识别方法研究()
分享到:

《江西师范大学学报》(自然科学版)[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2013年02期
页码:
120-124
栏目:
出版日期:
2013-03-01

文章信息/Info

Title:
A Study on Chinese Emotion Recognition Method
作者:
刘欢欢;李寿山;周国栋;李逸薇
苏州大学计算机科学与技术学院,江苏苏州,215006;香港理工大学中文及双语学系,香港,999077
Author(s):
LIU Huan-huan;LI Shou-shan;ZHOU Guo-dong;LI Yi-wei
关键词:
情绪识别特征工程分类方法不平衡分类集成学习
Keywords:
emotion recognitionfeature engineeringclassification methodimbalanced classificationensemble learning
分类号:
TP391
文献标志码:
A
摘要:
以中文情绪语料库(Ren-CECps)为基础,重点研究了句子级情绪识别方法.比较了不同特征以及不同机器学习分类方法(NB,SVM,ME)对情绪识别的影响.此外,针对情绪文本和非情绪文本在语料中的分布非常不平衡问题,通过集成学习的算法来实现不平衡情绪识别,用以提高情绪识别的整体性能.实验结果表明:使用基于样本的集成学习方法能够有效解决不平衡问题,明显提高情绪识别的分类性能.
Abstract:
The emotion recognition method at the sentence level is studied with a Chinese emotion corpus(Ren-CECps).Specifically has been investigated,the impact of different linguistic features as well as different classification methods(NB,SVM,ME)on the emotion recognition and classification has been compared.Moreover,they has proposed an ensemble learning approach to tackle the problem imbalanced data distribution of the emotion and non-emotion text.Experimental results have shown that the approach effectively enhances the performance of emotion recognition when the data distribution has been imbalanced.

参考文献/References:

[1] Aman S,Szpakowiczm S.Identifying expressions of emotion in text [EB/OL].
[2012-04-12].http:∥nlp.ipipan.waw.pl/NLP-SEMINAR/071029b.pdf.
[2] Castillo M,Serrano I.A muhistrategy approach for digital text categorization from imbalanced documents [EB/OL].
[2012-03-19].http:∥citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.98.6892&rep=rep1&type=pdf.
[3] Murphey Y,Wang H,Ou G et al.An effective algorithm for multi-class learning from imbalance data [EB/OL].
[2012-03-23].http:∥ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=04370991.
[4] Neviarouskaya A,Prendinger H,Ishizuka M.Textual affect sensing for sociable and expressive online communication [EB/OL].
[2012-04-19].http:∥citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.217.6182&rep=rep1&type=pdf.
[5] Pang B,Lee L,Vaithyanathan S.Thumbs up? sentiment classification using machine learning techniques [EB/OL].
[2012-04-22].http:∥www.cs.cornell.edu/home/llee/papers/sentiment.pdf.
[6] Quan Changqin,Ren Fuji.Construction of a blog emotion corpus for chinese emotional expression analysis [EB/OL].
[2012-06-17].http:∥www.aclweb.org/anthology/D09-1150.
[7] Quan Changqin,Ren Fuji.Sentence emotion analysis and recognition based on emotion words using Ren-CECps [J].International Journal of Advanced Intelligence,2010,2(1): 105-117.
[8]Shahshahani B,Landgrebe D.The effect of unlabeled samples in reducing the small sample size problem and mitigating the hughes phenomenon [J].Journals & Magazines,1994,32(5):1087-1095.
[9] Zheng Zhaohui,Wu Xiaoyun,Srihari R.Feature selection for text categorization on imbalanced data [J].SIGKDD Explorations,2004,6(1):80-89.
[10] 胡燕,吴虎子,钟珞.中文文本分类中基于词性的特征提取方法研究 [J].武汉理工大学学报,2007,29(4):132-135.
[11] 刘挺,车万翔,李生.基于最大熵分类器的语义角色标注 [J].软件学报,2007,18(3):565-573.
[12] 王中卿,李寿山,朱巧明,等.基于不平衡数据的中文情感分类 [J].中文信息学报,2012(3):33-37,64.
[13] 叶志飞,文益民,吕宝粮.不平衡分类问题研究综述 [J].智能系统学报,2009,4(2):148-156.

备注/Memo

备注/Memo:
国家自然科学基金(61003155,60873150);模式识别国家重点实验室开发课题基金
更新日期/Last Update: 1900-01-01