二维码（扫一下试试看！） | | 扩展语义相似情感词的文本情感分类方法 | | A Method of Text Sentiment Classification by Extending Semantic Similar Sentiment Words | | 投稿时间：2017-06-23 | | DOI：10.15918/j.tbit1001-0645.2018.11.009 | | 中文关键词:词嵌入Adaboost分类模型特征选择中文评论情感分类 | | English Keywords:word embedingAdaboost classification modelfeature selectionChinese commentsentiment classification | | 基金项目:北京理工大学基础研究基金资助项目（20160542013）；国家"二四二"计划项目（2017A149） | | | 摘要点击次数:649 | | 全文下载次数:333 | | 中文摘要: | | 针对文本情感分类中情感语义特征利用不足、特征降维效果欠佳等影响分类效果的问题，提出了一种通过扩展语义相似的情感词以及引入词语间统计特征的高精度网络评论情感分类方法.该方法利用神经网络Skip-gram模型生成词嵌入，通过词嵌入相似性度量将语义相似的词语扩展为情感特征；再利用词语间的统计特征进行特征降维；通过多个弱分器加权构建Adaboost分类模型实现网络评论情感分类.基于酒店评论和手机评论公开测试集进行实验，结果表明其情感分类的正确率分别达到90.96%和93.67%.方法扩展语义相似情感词有利于丰富文本情感语义特征，引入词语间的统计特征有更好的特征降维效果，可以进一步提升文本情感分类的效果. | | English Summary: | | To solve the effect problem of sentiment classification due to the insufficient use of emotional semantic features and unpromising dimension reduction effects, a novel high-precision sentiment classification method was proposed in this paper for online comments by extending semantic similar emotional words and employing the statistical features between words. Firstly, a neural network skip-gram model was employed to generate word embedding and extend the semantic similar words to emotional feature by the measure of embedding word similarity. Then the feature dimension was reduced by employing the statistical features between words. At last, sentiment classification of online comments was carried out by the Adaboost classification model which was constructed by weighting multiple weak classifiers. Experiment results on hotel reviews and mobile comments show that, the accuracy of sentiment classification with new method can reach 90.96% and 93.67% respectively. Expanding semantic similarity emotion words is helpful to enrich the semantic features of emotion. Employing statistical features between words has better feature reduction effect. Both two procedures effectively improve the performance of text sentiment classification. | | 查看全文查看/发表评论下载PDF阅读器 | |
莫根林,金永喜,王雪娇,李忠新,吴志林.步枪弹侵彻明胶的空间弹道模型和实验研究[J].北京理工大学学报（自然科学版）,2018,38(12):1244~1251,1295.MOGen-lin,JINYong-xi,WANGXue-jiao,LIZhong-xin,WUZhi-lin.Ballisti ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21刘雪岭,张奇.正烷烃液体云雾最小点火能实验研究[J].北京理工大学学报（自然科学版）,2018,38(12):1252~1255,1320.LIUXue-ling,ZHANGQi.ExperimentalStudyonMinimumIgnitionEnergyofn-AlkaneMists[J].T ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21.北京理工大学学报2018年总目次（第38卷）[J].北京理工大学学报（自然科学版）,2018,38(12):1321~1338..[J].TransactionsofBeijingInstituteofTechnology,2018,38(12):1321-1338.二维码（扫一下试试看！）北京理 ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21钟巍,寿列枫,田宙,浦锡锋,何增,李伟昌,刘俊,王仲琦.钢化玻璃冲击波毁伤实验中的碎片规律研究[J].北京理工大学学报（自然科学版）,2018,38(S2):151~155.ZHONGWei,SHOULie-feng,TIANZhou,PUXi-feng,HEZeng,LIWei-chang,LIU ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21王远芳,张世潇,仝毅.熔融离心法分离退役梯黑铝炸药TNT组分的实验探究[J].北京理工大学学报（自然科学版）,2018,38(S2):198~204.WANGYuan-fang,ZHANGShi-xiao,TONGYi.StudyonSeparationofTNTFromWasteorObsolet ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21陈岳坪,靳龙,卢海燕,冯志君,谌炎辉.空间统计方法在自由曲面加工误差分解中的应用[J].北京理工大学学报（自然科学版）,2017,37(3):260~266.CHENYue-ping,JINLong,LUHai-yan,FENGZhi-jun,CHENYan-hui.ApplicationofSpa ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21黄珊,徐诚,温垚珂,豆恂.典型小口径步枪弹侵彻明胶时空腔演化规律的实验研究[J].北京理工大学学报（自然科学版）,2017,37(4):342~347.HUANGShan,XUCheng,WENYao-ke,DOUXun.ExperimentalStudyontheEvolutionoftheTem ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21肖艳文,徐峰悦,郑元枫,余庆波,王海福.活性材料弹丸碰撞油箱引燃效应实验研究[J].北京理工大学学报（自然科学版）,2017,37(6):557~561.XIAOYan-wen,XUFeng-yue,ZHENGYuan-feng,YUQing-bo,WANGHai-fu.ExperimentalSt ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21胡俊,李婷婷,于勇,姜建玉.环形与圆形喷管水下气泡生成的实验对比研究[J].北京理工大学学报（自然科学版）,2017,37(8):771~777.HUJun,LITing-ting,YUYong,JIANGJian-yu.ExperimentalInvestigationofSubmergedBub ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21张程焱,卢继平.刀-屑局部摩擦因数建模及实验研究[J].北京理工大学学报（自然科学版）,2017,37(9):899~904.ZHANGCheng-yan,LUJi-ping.ModelingandExperimentalInvestigationonLocalFrictionCoefficient ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21
| |
