[1]王义真,郑 啸,后 盾,等.基于SVM 的高维混合特征短文本情感分类[J].计算机技术与发展,2018,28(02):88-93.[doi:10．3969/j．issn．1673－629X．2018．02．020]
　WANG Yi-zhen,ZHENG Xiao,HOU Dun,et al.Short Text Sentiment Classification of High Dimensional Hybrid Feature Based on SVM[J].,2018,28(02):88-93.[doi:10．3969/j．issn．1673－629X．2018．02．020]
点击复制

基于SVM 的高维混合特征短文本情感分类()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年02期
页码:
88-93
栏目:
智能、算法、系统工程
出版日期:
2018-02-10

文章信息/Info

Title:
Short Text Sentiment Classification of High Dimensional Hybrid Feature Based on SVM
文章编号:
1673－629X(2018)02－0088－06
作者:
王义真; 郑 啸; 后 盾; 胡 昊
安徽工业大学 计算机科学与技术学院，安徽 马鞍山 243032
Author(s):
WANG Yi-zhen; ZHENG Xiao; HOU Dun; HU Hao
School of Computer Science and Technology，Anhui University of Technology，Ma’anshan 243032，China
关键词:
情感分类; 混合特征; 支持向量机; 情感词典
Keywords:
sentiment classification; hybrid feature; SVM; emotion dictionary
分类号:
TP393
DOI:
10．3969/j．issn．1673－629X．2018．02．020
文献标志码:
A
摘要:
针对短文本具有的稀疏性、不规范性、主题不明确性等相关特点，提出一种基于 SVM 的高维混合特征模型。首先介绍了兼顾语义和情感的 6 类特征:表情符号特征、词聚类特征、词性标注特征、n－gram 特征、否定特征和情感词典。其中主要介绍了该 6 类特征的概念、抽取方式以及输出形式;其次在第六届中文倾向性分析评测(COAE2014)为基础的数据集上，采用 5 折交叉的方法对该模型进行了有效性验证，其平均准确率为 84．69%、平均召回率为 83．13%，而平均 F 1 值为 83．90%;接着探讨了 SVM 惩罚系数对实验的影响;最后将该模型与一步三分类方法、Ｒecursive Auto Encoder、Doc2vec 做了对比分析，结果表明提出的模型对短文本情感分类更有效。
Abstract:
Aiming at the characteristics of short texts which are sparse，unnormative and ambiguous in subject，we present a hybrid feature model with high dimension based on SVM．Firstly，we introduce six types of feature about both semantics and emotion，involving expression symbols，word clustering symbols，part－of－speech tagging，n－gram，negation and the sentiment dictionary，which are mainly introduced in their concept，extraction and output form．Then a five－fold crossover method is used to verify the validity of the model according to the data of COAE2014．The average accuracy rate is 84．69%，the average recall rate is 83．13%，and the average F 1 value is 83．90%．Thirdly，we discuss the influence of SVM regularization parameter on experiment．Finally，the proposed model is compared and analyzed with Ｒecursive Auto Encoder，Doc2vec and so on，which show that it is more effective for short text emotion classification．

相似文献/References:

[1]陈锦禾 范新 沈闻 沈洁.基于情感词识别的BBS情感分类研究[J].计算机技术与发展,2009,(07):120.
　CHEN Jin-he,FAN Xin,SHEN Wen,et al.Research on Sentiment Classification of BBS Reviews Based on Identifying Words with Polarity[J].,2009,(02):120.
[2]章国宝 宋清华 费树岷 赵艳.语音情感识别研究[J].计算机技术与发展,2009,(01):92.
　ZHANG Guo-bao,SONG Qing-hua,FEI Shu-min,et al.Study of Emotional Speech Recognition[J].,2009,(02):92.
[3]魏华珍[],戴安娜[],赵姝[][]. 基于领域覆盖算法的音乐情感识别[J].计算机技术与发展,2014,24(07):72.
　WEI Hua-zhen[],DAI An-na[],ZHAO Shu[][]. Music Emotion Recognition Based on Neighborhood Covering Algorithm[J].,2014,24(02):72.
[4]郑文静,李雷. 基于聚类核的半监督情感分类算法研究[J].计算机技术与发展,2016,26(12):87.
　ZHENG Wen-jing,LI Lei. Research on Semi-supervised Sentiment Classification Based on Cluster Kernel[J].,2016,26(02):87.
[5]吴潇[],王磊[][]. 基于购物领域词典扩建的评论情感研究[J].计算机技术与发展,2017,27(07):194.
　WU Xiao[],WANG Lei[][]. Investigation on Sentiment of Reviews with Shopping Field Dictionary Construction[J].,2017,27(02):194.
[6]孙悦,李晶,吴铁峰,等.基于卷积神经网络的短评语情感分类[J].计算机技术与发展,2018,28(11):61.[doi:10.3969/ j. issn.1673-629X.2018.11.014]
　SUN Yue,LI Jing,WU Tie-feng,et al.Classification of Short Comment Emotion Based on Convolutional Neural Network[J].,2018,28(02):61.[doi:10.3969/ j. issn.1673-629X.2018.11.014]
[7]宋祖康,阎瑞霞.基于 CNN-BIGRU 的中文文本情感分类模型[J].计算机技术与发展,2020,30(02):166.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 032]
　SONG Zu-kang,YAN Rui-xia.Chinese Comment Sentiment Classification Model Based on CNN-BIGRU[J].,2020,30(02):166.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 032]
[8]雷梦宁,丁爱玲,王新美,等.基于混合特征值的托攻击检测算法[J].计算机技术与发展,2021,31(10):87.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 015]
　LEI Meng-ning,DING Ai-ling,WANG Xin-mei,et al.Shilling Attack Detection Algorithm Based on Hybrid Eigenvalue[J].,2021,31(02):87.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 015]

更新日期/Last Update: 2018-03-28