Please wait a minute...
Advanced Search
现代图书情报技术  2016, Vol. 32 Issue (2): 16-24     https://doi.org/10.11925/infotech.1003-3513.2016.02.03
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
中文评论产品特征与观点抽取方法研究*
孟园(),王洪伟
同济大学经济与管理学院 上海 210000
Extracting Product Feature and User Opinion from Chinese Reviews
Yuan Meng(),Hongwei Wang
School of Economics and Management, Tongji University, Shanghai 210000, China
全文: PDF (522 KB)   HTML ( 137
输出: BibTeX | EndNote (RIS)      
摘要 

目的】针对中文在线评论产品特征与观点抽取问题, 提出一种基于置信度排序模型的抽取方法。【方法】在改进HITS算法基础上, 综合考虑候选特征观点词的关联关系和语义关系构建置信度排序模型, 提取并过滤特征观点词。【结果】和基准模型相比, 本文方法对中文语料的产品特征和观点抽取能达到较高准确率和召回率。【局限】仅针对产品显性特征抽取, 没有考虑隐性特征的识别与抽取。【结论】利用特征词和观点词的双向增强关系和语义关系, 可以有效抽取产品特征观点; 情感极性过滤对提升观点词抽取准确率有较大作用。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
孟园
王洪伟
关键词 置信度排序HITS关联关系语义关系双向增强关系特征观点抽取    
Abstract

[Objective] This study proposed a confidence ranking model to extract product feature and user opinion from the Chinese online reviews. [Methods] Examining the semantic and association relations between candidate words, we built the confidence ranking model based on the improved HITS algorithm, and then retrieved the feature and opinion words. [Results] Compared with the reference model, our method showed better recall and precision rates while extracting the feature and opinion words from the Chinese corpus. [Limitations] Only extracted the explicit feature and opinion words, and did not try to identify and extract the implicit ones. [Conclusions] We could effectively extract the feature and opinion words using their mutual reinforcement and semantic relations. Filtering method of the semantic polarity could also improve the precision of the extracted opinion words.

Key wordsConfidence ranking    HITS    Association relation    Semantic relation    Mutual reinforcement    Feature opinion extraction
收稿日期: 2015-08-28      出版日期: 2016-03-08
基金资助:*本文系国家自然科学基金项目“中文语境下基于模糊本体的用户在线评论的情感分析”(项目编号:70971099)和国家自然科学基金项目“在线评论对商家业绩的影响研究:情感分析的视角”(项目编号:71371144)的研究成果之一
引用本文:   
孟园, 王洪伟. 中文评论产品特征与观点抽取方法研究*[J]. 现代图书情报技术, 2016, 32(2): 16-24.
Yuan Meng, Hongwei Wang. Extracting Product Feature and User Opinion from Chinese Reviews. New Technology of Library and Information Service, 2016, 32(2): 16-24.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.1003-3513.2016.02.03      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2016/V32/I2/16
[1] 王永, 张勤, 杨晓洁. 中文网络评论中产品特征提取方法研究[J]. 现代图书情报技术, 2013(12): 70-73.
[1] (Wang Yong, Zhang Qin, Yang Xiaojie.Research on the Method of Extracting Features from Chinese Product Reviews on the Internet[J]. New Technology of Library and Information Service, 2013(12): 70-73.)
[2] Zhang L, Liu B, Lim S H, et al.Extracting and Ranking Product Features in Opinion Documents [C]. In: Proceedings of the 23rd International Conference on Computational Lingusitics (COLING), Beijing, China. Stroudsburg, PA, USA: ACL, 2010: 1462-1470.
[3] 郗亚辉. 产品评论特征及观点抽取研究[J]. 情报学报, 2014, 33(3): 326-336.
[3] (Xi Yahui.Extracting Product Features and Opinions from Product Reviews[J]. Journal of the China Society for Scientific and Technical Information, 2014, 33(3): 326-336.)
[4] Jin W, Ho H H, Srihari R K.A Novel Lexicalized HMM-based Learning Framework for Web Opinion Mining [C]. In: Proceedings of the 26th Annual International Conference on Machine Learning (ICML), Montreal, Canada. New York, NY, USA: ACM, 2009: 465-472.
[5] Li F T, Han C, Huang M L, et al.Structure-aware Review Mining and Summarization [C]. In: Proceedings of the 23rd International Conference on Computational Linguistics (COLING), Beijing, China. Stroudsburg, PA, USA: ACL, 2010: 653-661.
[6] Wu Y B, Zhang Q, Huang X J, et al.Phrase Dependency Parsing for Opinion Mining [C]. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing (EMNLP), Singapore. Morristown, NJ, USA: ACL, 2009: 1533-1541.
[7] Titov I, McDonald R. Modeling Online Reviews with Multi-grain Topic Models [C]. In: Proceedings of the 17th International Conference on World Wide Web (WWW), Beijing, China. New York, NY, USA: ACM, 2008: 111-120.
[8] Zhao W X, Jiang J, Yan H F, et al.Jointly Modeling Aspects and Opinions with a MaxEnt-LDA Hybrid [C]. In: Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing (EMNLP), Massachusetts, USA. Stroudsburg, PA, USA: ACL, 2010: 56-65.
[9] Hu M Q, Liu B.Mining and Summarizing Customer Reviews[C]. In: Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), Seattle, USA. New York, NY, USA: ACM, 2004: 168-177.
[10] Aravindan S, Ekbal A.Feature Extraction and Opinion Mining in Online Product Reviews [C]. In: Proceedings of the 2014 International Conference on Information Technology (ICIT), Bhubaneswar, India. New York, NY, USA: IEEE, 2014: 94-99.
[11] Qiu G, Liu B, Bu J J, et al.Opinion Word Expansion and Target Extraction Through Double Propagation[J]. Computational Linguistics, 2011, 37(1): 9-27.
[12] Hai Z, Chang K Y, Cong G.An Association-Based Unified Framework for Mining Features and Opinion Words[J]. ACM Transaction on Intelligent Systems and Technology, 2015, 6(2): 2601-2626.
[13] Liu K, Xu L H, Zhao J.Extracting Opinion Targets and Opinon Words from Online Reviews with Graph Co-ranking [C]. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Ligustics (ACL), Baltimore, USA. Stroudsburg, PA, USA: ACL, 2014: 314-324.
[14] 尹裴, 王洪伟, 郭恺强. 中文产品评论的“特征观点对”识别: 基于领域本体的建模方法[J]. 系统工程, 2013, 31(1): 68-77.
[14] (Yin Pei, Wang Hongwei, Guo Kaiqiang.Feature- opinion Pair Identification in Chinese Online Reviews Based on Domain Ontology Modeling Method[J]. Systems Engineering, 2013, 31(1): 68-77.)
[15] 郑波, 胡其, 林君. 文本语义分析的实现及应用[J]. 程序员, 2013(7): 105-109.
[15] (Zheng Bo, Hu Qi, Lin Jun.Implementation and Application of Semantic Analysis in Text[J]. Programmer, 2013(7): 105-109.)
[16] Kansal H, Toshniwal D.Aspect Based Summarization of Context Dependent Opinion Words[J]. Procedia Computer Science, 2014, 35: 166-175.
[17] 哈工大-讯飞语言云. Web Service接口[EB/OL]. [2015-05-01]. .
[17] (LTP-Cloud RESTful API [EB/OL]. [2015-05-01].
[1] 田钟林,吴旭,颉夏青,许晋,陆月明. 一种基于领域语义关系图的短文本实时分析模型*[J]. 数据分析与知识发现, 2020, 4(2/3): 239-248.
[2] 牟冬梅, 金姗, 琚沅红. 基于文献数据的疾病与基因关联关系研究*[J]. 数据分析与知识发现, 2018, 2(8): 98-106.
[3] 谢靖, 王敬东, 吴振新, 张智雄, 王颖, 叶志飞. 科技文献检索系统语义丰富化框架的设计与实践*[J]. 数据分析与知识发现, 2017, 1(4): 84-93.
[4] 李晓瑛,夏光辉,李丹亚. 主题标引文献的语义关系发现研究*[J]. 现代图书情报技术, 2016, 32(7-8): 87-93.
[5] 翟东升, 刘鹤, 张杰, 蔡力伟. 基于图形数据库的专利语义知识库构建技术研究[J]. 数据分析与知识发现, 2016, 32(12): 66-75.
[6] 熊涛, 何跃. 微博转发网络中意见领袖的识别与分析[J]. 现代图书情报技术, 2013, (6): 55-62.
[7] 王秀艳, 崔雷. 采用混合方法抽取生物医学实体间语义关系[J]. 现代图书情报技术, 2013, 29(3): 77-82.
[8] 周杰, 刘玉琴, 曾建勋. 学术研究主体与研究内容间的关联关系可视化方法[J]. 现代图书情报技术, 2012, (11): 92-97.
[9] 王秀艳, 崔雷. 应用关键动词抽取生物医学实体间语义关系研究综述[J]. 现代图书情报技术, 2011, 27(9): 21-27.
[10] 刘建华,张智雄. 基于Stanford Parser的实体间关系识别[J]. 现代图书情报技术, 2009, 25(5): 1-5.
[11] 田光明,刘艳玲. FrameNet框架之间的关系分析*[J]. 现代图书情报技术, 2008, 24(6): 1-5.
[12] 周鑫,王军. 基于概念外延的Folksonomy语义关系挖掘方法[J]. 现代图书情报技术, 2008, 24(10): 6-10.
[13] 张晗,路振宇,崔雷 . 利用关联规则对医学文本数据库进行知识抽取的尝试*——以四种抗肿瘤药为例[J]. 现代图书情报技术, 2006, 1(9): 49-52.
[14] 王子熙,马蕾 . 《汉语主题词表》词间关系的可视化[J]. 现代图书情报技术, 2006, 1(3): 86-88.
[15] 陈定权. 基于超链分析的查找相关网页算法[J]. 现代图书情报技术, 2004, 20(2): 42-45.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn