[1]陈岳峰,苗夺谦,李文,等.基于概念的词汇情感倾向识别方法[J].智能系统学报,2011,6(06):489-494.
 CHEN Yuefeng,MIAO Duoqian,LI Wen,et al.Semantic orientation computing based on concepts[J].CAAI Transactions on Intelligent Systems,2011,6(06):489-494.
点击复制

基于概念的词汇情感倾向识别方法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第6卷
期数:
2011年06期
页码:
489-494
栏目:
出版日期:
2011-12-25

文章信息/Info

Title:
Semantic orientation computing based on concepts
文章编号:
1673-4785(2011)06-0489-06
作者:
陈岳峰12苗夺谦12李文12张志飞12
1.同济大学 计算机科学与技术系,上海 201804;
2.同济大学 嵌入式系统与服务计算教育部重点实验室,上海 200092
Author(s):
CHEN Yuefeng 12 MIAO Duoqian 12 LI Wen 12 ZHANG Zhifei 12
1.Department of Computer Science and Technology, Tongji University, Shanghai 201804, China;
2.The Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai 200092, China
关键词:
文本倾向性分析HowNet概念聚类KMEDOIDS
Keywords:
sentiment analysis HowNet concept clustering KMedoids
分类号:
TP391
文献标志码:
A
摘要:
词汇的语义倾向是文本倾向性分析的基础课题.现有的词汇语义倾向计算通常是以词汇为基准,而词是包括了多种不同情感倾向概念的粒度范畴,影响分析的精度和效率.据此,提出在更细的粒度下,利用HowNet工具中的“概念”进行倾向性分析,设计了基于概念的语义倾向计算方法.该方法使用聚类的概念,利用KMEDOIDS算法寻找基准概念.实验结果表明,基于概念的方法较传统基于词汇的方法准确率更高.
Abstract:
The semantic orientation of words is the foundation of sentiment analysis. Current methods to compute semantic orientation of words are mostly based on reference words, while words belonging to the granularity category, including various sentiment orientation concepts, affect the analytical precision and efficiency. In this paper, a new method of semantic orientation computing was proposed based on the reference concepts using the HowNet tool to analyze the tendency. The clustering algorithm KMediods was used to search for the reference concepts. The experimental results show that the conceptbased method outperforms the wordbased method.

参考文献/References:

[1]HATZIVASSILOGLOU V, MCKEOWN K. Predicting the semantic orientation of adjectives[C]//Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and the 8th Conference of the European Chapter of the ACL. New Brunswick, Canada, 1997: 174181.
[2]TURNEY P. Thumbs up or thumbs down? semantic orientation applied to unsupervised classification of reviews[C]//Proceedings of the 40 th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA, 2002: 417424.
[3]TURNEY P, LITTMAN M. Measuring praise and criticism: inference of semantic orientation from association[J]. ACM Transactions on nformation Systems, 2003, 21 (4): 315346.
[4]JAAP K, MAARTEN M, ROBERT J M, De RIJKE M. Using WordNet to measure semantic orientations of adjectives[C]//Proceedings of the Fourth International Conference on Language Resources and Evaluation. Lisbon, Portugal, 2004, IV: 11151118.
[5]赵妍妍, 秦兵, 刘挺. 文本情感分析[J]. 软件学报, 2010, 21 (8): 18341848.
ZHAO Yanyan, QIN Bing, LIU Ting. Sentiment analysis[J]. Journal of Software, 2010, 21 (8): 18341848. 
[6]王素格. 基于Web的评论文本情感分类问题研究[D].上海:上海大学, 2008:2124.
WANG Suge. Research on problems for sentiment classification of review texts based on web[D]. Shanghai: Shanghai University, 2008: 2124.
[7]朱嫣岚, 闵锦, 周雅倩,等. 基于HowNet 的词汇语义倾向计算[J]. 中文信息学报, 2006, 20(1):1420.
ZHU Yanlan, MIN Jin, ZHOU Yaqian, et al. Semantic orientation computing based on HowNet[J]. Journal of Chinese Information Processing, 2006, 20(1): 1420.
[8]杨昱昺,吴贤伟. 改进的基于知网词汇语义褒贬倾向性计算[J]. 计算机工程与应用, 2009, 45(21): 9193.
YANG Yubing, WU Xianwei. Improved lexical semantic tendentiousness recognition computing[J]. Computer Engineering and Applications, 2009, 45(21): 9193. 
[9]熊德平,程菊明, 田胜利. 基于HowNet的句子褒贬倾向性计算[C]//中国人工智能学会第12届全国学术年会, 哈尔滨, 2007: 910913.
 XIONG Deping, CHENG Juming, TIAN Shengli. Sentence orientation research based on HowNet[C]// Proceedings of the 12th Annual Meeting of Chinese Association for Artificial Intelligence. Harbin, 2007: 910913.
[10]刘群,李素建. 基于《知网》的词汇语义相似度的计算[C]//第3届汉语词汇语义学研讨会. 台北,中国, 2002: 5976.
LIU Qun, LI Sujian. Word similarity computing based on Hownet[C]//The 3rd Chinese Lexical Semantics Workshop. Taipei, China, 2002: 5976. 
[11]JAIN K, MURTY M N, FLYNN P J. Data clustering: a review[J]. ACM Computing Surveys, 1999, 31(3): 264323.

相似文献/References:

[1]杨春燕,李卫华,汤龙,等.基于可拓学和HowNet的策略生成系统研究进展[J].智能系统学报,2015,10(6):823.[doi:10.11992/tis.201507057]
 YANG Chunyan,LI Weihua,TANG Long,et al.Strategy-generating system based on Extenics and HowNet[J].CAAI Transactions on Intelligent Systems,2015,10(06):823.[doi:10.11992/tis.201507057]

备注/Memo

备注/Memo:
收稿日期: 2011-03-15.
基金项目:国家自然科学基金资助项目(60970061, 61075056, 61103067);上海市重点学科建设资助项目(B004);中央高校基本科研业务费专项资金资助项目.
通信作者:陈岳峰.E-mail:dennislyve@gmail.com.
作者简介:
陈岳峰,男,1986年生,硕士研究生,主要研究方向为文本倾向性分析、文本信息处理、数据挖掘.
苗夺谦,男,1964年生,教授,博士生导师.中国计算机学会理事,中国人工智能学会理事,上海市计算机学会理事等.已主持完成多项国家级、省部级自然科学基金与科技攻关项目,并参与完成“973”计划项目1项,“863”计划项目2项等,曾获国家教委科技进步三等奖、山西省科技进步二等奖、教育部科技进步一等奖、上海市技术发明一等奖、重庆市自然科学一等奖等.主要研究方向为智能信息处理、粗糙集、粒计算、网络智能、数据挖掘等.发表学术论文140余篇,其中被SCI和EI检索70余篇,出版教材及学术著作6部,授权专利9项.
李文,女,1980年生,博士研究生,主要研究方向为文本信息处理、粗糙集、粒计算.
更新日期/Last Update: 2012-02-29