基于HNC语境框架和情感词典的文本情感倾向分析

doi:10.6040/j.issn.1671-9352.1.2015.E48

摘要/Abstract

摘要： 提出了一种基于情感词典和概念层次网络(hierarchical network concepts, HNC)语境框架的文本情感倾向性分析方法,将文本的情感倾向分析分为两个阶段:特征词、语句和句群判定阶段;基于HNC语境框架的句与句群情感分析阶段。首先以HowNet情感词典和自建的形容词配价词典(valency dictionary of English adjective, VDEA)作为基础词典资源进行文本特征词匹配,在此基础上基于HNC语境框架进行文本的情感倾向性判定,融合情感词典资源与HNC语境框架的独特优势,从特征词语情感分析入手,以包含特征词的语句及句群为情感分析重点,进而确定文本的情感倾向性,体现了HNC “有所为有所不为” 的思想。为验证方法的有效性,文本分别对政治、经济、体育与影视评论等领域文本进行测试,从实验结果可以看出商品评论以及影评类的文本情感识别率相对较高,而政治与体育类识别率低,但基本达到了预期实验效果,从而验证了本方法的可行性。

关键词: 情感词典, HNC, 倾向性分析, 语境框架

Abstract: Based on the current sentimental dictionaries and HNC contextual framework, a method of text sentimental orientation analysis was put for ward. The sentimental analysis process covers two phases: feature words matching and feature sentence(or sentence group)finding; feature sentence or sentence group sentimental analysis based on HNC contextual framework. In the first phase, sentimental dictionary of HowNet and Valency Dictionary of English Adjective(VDEA)are applied while the feature sentence or sentence group are analyzed in the second phase. The method, through exact matching of feature words, makes the posterior processing work more effective energy-focused because only those sentences or sentence groups containing subjective sentiment can be analyzed and processed. This thought also illustrates one of the spirits of HNC: doing certain things and refraining from doing other things. The paper takes texts concerning politics, economy,sports and films’ comments as experimental data and experiment result shows that sentimental orientation recognition rate of texts concerning goods and film comments are higher than that politics and sports. The expected experimental results of the paper is reached, which tested the feasibility of the method.

Key words: HNC, contextual framework, sentimental orientation analysis, sentimental dictionary

中图分类号:

TP309

张克亮,黄金柱,曹蓉,李峰. 基于HNC语境框架和情感词典的文本情感倾向分析[J]. 山东大学学报（理学版）, 2016, 51(7): 51-58.

ZHANG Ke-liang, HUANG Jin-zhu, CAO Rong, LI Feng. Text sentimental orientation analysis based on HNC contextual framework and sentimental dictionaries[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2016, 51(7): 51-58.

参考文献

[1] 黄萱菁,张奇,吴苑斌.文本情感倾向分析[J].中文信息学报,2011,25(6):118-126. HUANG Xuanjing, ZHANG Qi, WU Yuanbin. Text sentiment analysis[J]. Chinese Journal of Information, 2011, 25(6):118-126.
[2] 刘群,李素建. 基于《知网》的词汇语义相似度的计算[J].中文计算语言学, 2002,7(2):59-76. LIU Qun, LI Sujian. Based on the “HowNet” vocabulary semantic similarity calculation[J]. Computational Linguistics in Chinese, 2002, 7(2):59-76.
[3] 熊德兰,程菊明,田胜利.基于HowNet的句子褒贬倾向性研究[J].计算机工程与应用, 2008, 44(22):143-145. XIONG Delan, CHENG Juming, TIAN Shengli. Study on sentence orientation based on HowNet[J]. Computer Engineering and Applications, 2008, 44(22):143-145.
[4] 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,2007,20(1):14-20. ZHU Yanlan, MIN Jin, ZHOU Yaqian, et al. Computation of lexical semantic orientation based on HowNet[J]. Chinese Journal of information, 2007, 20(1):14-20.
[5] 于潇,万军,何翔,等.校园微博情感分析系统的设计与实现[J].河北工业大学学报,2013,42(6):24-29. YU Xiao, WAN Jun, HE Xiang, et al. Design and implementation of campus micro-blog emotion analysis system[J]. Journal of Hebei University of Technology, 2013, 42(6):24-29.
[6] 王兰成,徐震.基于情感本体的主题网络舆情倾向性分析[J].信息与控制, 2013,42(1):46-52. WANG Lancheng, XU Zhen. An analysis of the topic network public opinion tendency based on emotion ontology[J]. Information and Control, 2013, 42(1):46-52.
[7] 董丽丽,赵繁荣,张翔.基于领域本体、情感词典的商品评论倾向性分析[J].计算机应用与软件,2014,31(12):104-108. DONG Lili, ZHAO Fanrong, ZHANG Xiang. The analysis of the tendency of commodity review based on domain ontology and sentiment dictionary[J]. Computer Applications and Software, 2014, 31(12):104-108.
[8] 周咏梅,杨佳能.面向文本情感分析的中文情感词典构建方法[J].山东大学学报(工学版), 2013,23(6):27-33. ZHOU Yongmei, YANG Jianeng. Construction method of Chinese emotion dictionary for text sentiment analysis[J]. Journal of Shandong University(Engineering Science), 2013, 23(6):27-33.
[9] 潘文彬.基于情感词典的中文句子情感倾向分析[D].北京:北京邮电大学, 2011. PAN Wenbin. Sentiment orientation of Chinese sentences based on sentiment dictionary[D]. Beijing: Beijing University of Posts and Telecommunications, 2011.
[10] 黄硕.中文情感知识库的构建与应用[D]. 北京:北京邮电大学, 2013. HUANG Shuo. Construction and application of Chinese emotion knowledge base[D]. Beijing: Beijing University of Posts and Telecommunications, 2013.
[11] 张成功,刘培玉,朱振方,等.一种基于极性词典的情感分析方法[J].山东大学学报(理学版), 2012, 47(3):47-50. ZHANG Chenggong, LIU Peiyu, ZHU Zhenfang, et al. An emotional analysis method based on polar dictionary [J]. Journal of Shandong University(Natural Science), 2012, 47(3):47-50.
[12] 徐晓丹,段正杰,陈中育.基于扩展情感词典及特征加权的情感挖掘方法[J].山东大学学报(工学版),2014,44(6):16-18. XU Xiaodan, DUAN Zhengjie, CHEN Zhongyu. Emotion mining based on extended emotion dictionary and feature weighting[J]. Journal of Shandong University(Engineering Science), 2014, 44(6):16-18.
[13] 刘梅彦,张仰森,张涛.基于语义分析的不良倾向文本的识别算法研究[J].北京信息科技大学学报,2014,29(4):16-20. LIU Meiyan, ZHANG Yangsen, ZHANG Tao. Research on recognition algorithm of bad tendency text based on semantic analysis[J]. Journal of Beijing Information Science and Technology University, 2014, 29(4):16-20.
[14] 晋耀红.概念层次网络(HNC)语言理解技术及应用[J].云南师范大学学报,2010,42(4):19-23. JIN Yaohong. Concept hierarchy network(HNC)language understanding technology and its application[J]. Journal of Yunnan Normal University, 2010, 42(4):19-23.
[15] 晋耀红.HNC(概念层次网络)语言理解技术及应用[M].北京: 科学出版社,2006. JIN Yaohong. HNC(conceptual level network)language understanding technology and its application[M]. Beijing: Science Press, 2006.
[16] 晋耀红.基于语境框架的文本相似度计算[J].计算机工程与应用,2004(16):36-39. JIN Yaohong. Text similarity computation based on context framework[J]. Computer Engineering and Applications, 2004(16):36-39.
[17] 韦向峰,张全,缪建明,等.基于语义块的事件倾向性分析研究[J].中文信息学报,2012,26(3):44-48. WEI Xiangfeng, ZHANG Quan, MIAO Jianming, et al. An analysis of event orientation based on semantic chunks[J]. Chinese Journal of Information, 2012, 26(3):44-48.
[18] 张克亮.基于HNC理论的句法结构歧义消解[J]. 中文信息学报,2004,18(6):43-52. ZHANG Keliang. Ambiguity resolution of syntactic structure based on HNC theory[J]. Chinese Journal of Information, 2004, 18(6):43-52.
[19] 唐兴全,王敬成,白晓革,等.HNC反色情知识库建设[C] // 全国第八届计算语言学联合学术会议(JSCL-2005)论文集.北京:中国中文信息学会, 2005, 8:660-662. TANG Xingquan, WANG Jingcheng, BAI Xiaoge, et al. HNC anti pornography knowledge base construction[C] // Proceedings of the Eighth National Conference on Computational Linguistics(JSCL-2005). Beijing: Chinese Information Processing Society of China, 2005, 8:660-662.
[20] 王文峰,唐兴全.基于HNC语境理论的文本分类[C] // 第七届中文信息处理国际会议论文集.北京:中国中文信息学会,2007:488-493. WANG Wenfeng, TANG Xingquan.The text classifying based on the HNC theory[C] //Proceedings of International Conference on Chinese Computing(ICCC2007). Beijing: Chinese Information Processing Society of China, 2007:488-493.
[21] 刘玉娇,琚生根,伍少梅,等.基于情感字典与连词结合的中文文本情感分类[J].四川大学学报(自然科学版),2015(1):57-62. LIU Yujiao, JU Shenggen, WU Shaomei, et al. Sentiment classification of Chinese texts based on emotion dictionary and conjunction[J]. Journal of Sichuan University(Natural Science Edition), 2015(1):57-62.
[22] 刘玮楠.基于HNC理论的网购评论情感倾向性分析研究[D].大连:大连理工大学,2013. LIU Weinan. Analysis of the emotion tendency of online shopping reviews based on HNC theory[D]. Dalian:Dalian University of Technology, 2013.
[23] 缪建明,张全.HNC语境框架及其语境歧义消解[J].计算机工程,2007,33(15):10-13. MIAO Jianming, ZHANG Quan. HNC context frame and context disambiguity[J]. Computer Engineering, 2007, 33(15):10-13.
[24] HUANG Jinzhu, YI Mianzhu. The design and implementation of VDEA[J]. International Universal Communication Symposium, 2010: 325-331.
[25] 朱倩,史燕,程显毅,等. 基于HNC词的聚类[J].郑州大学学报(理学版),2009,41(2):44-47. ZHU Qian, SHI Yan, CHENG Xianyi, et al. Clustering based on HNC words[J]. Journal of Zhengzhou University(Natural Science Edition), 2009, 41(2):44-47.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed