Please wait a minute...
New Technology of Library and Information Service  2014, Vol. 30 Issue (12): 44-50    DOI: 10.11925/infotech.1003-3513.2014.12.06
Current Issue | Archive | Adv Search |
Using Dependency Parsing Pattern to Extract Product Feature Tags
Nie Hui, Du Jiazhong
School of Information Management, Sun Yat-Sen University, Guangzhou 510006, China
Download:
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] The method of association recognition for features and the relevant opinions is investigated in order to extract features tags and summarize users' generated online reviews, which is helpful for Web users to access useful information effectively, especially when online information normally varies greatly in quality. [Methods] The dependency parsing is employed to obtain the extraction templates, the template library is constructed after the processes of classifying, filtering and generalization. In terms of the templates and the corresponding external lexicons, feature tags are extracted and sifted out according to the filtering rules. [Results] The experiment results indicate that the method outperforms the similar one which is only based on templates filtration or generalization. The performance of F-measure achieves 56.5% and the accuracy could reach 65% by adjusting the corresponding parameters. [Limitations] The filtering strategy for improving the quality of review data is not conducted in the research. Building feature lexicon automatically and adding more syntactic relations need to consider to extend the library of templates and make improvement of extraction accuracy further. [Conclusions] The better performance can be achieved by finding the most appropriate values for the template-specific parameters, such as the length of template, or by adopting an effective filtering window strategy to detect the noise templates.

Key wordsReview mining      Tags extraction      Dependency parsing analysis     
Received: 23 June 2014      Published: 20 January 2015
:  TP391  

Cite this article:

Nie Hui, Du Jiazhong. Using Dependency Parsing Pattern to Extract Product Feature Tags. New Technology of Library and Information Service, 2014, 30(12): 44-50.

URL:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.1003-3513.2014.12.06     OR     https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2014/V30/I12/44

[1] 中国互联网络发展状况统计报告(2014年7月) [EB/OL]. [2014-07-29]. http://www.cnnic.net.cn/gywm/xwzx/rdxw/2014/ 201407/W020140721559080702009.pdf. (China Internet Network Development State Statistical Report [EB/OL]. [2014-07-29]. http://www.cnnic.net.cn/gywm/xwzx/rdxw/ 2014/201407/W020140721559080702009.pdf.)
[2] 蒋音播. 消费者网络口碑传播的动机研究[D]. 武汉: 华中科技大学, 2009. (Jiang Yinbo. The Motivation of the Spread of Electronic Word-of-Mouth [D]. Wuhan: Huazhong University of Science & Technology, 2009.)
[3] Liu B. Sentiment Analysis and Opinion Mining [M]. Morgan & Claypool Publishers, 2012.
[4] Hu M, Liu B. Mining and Summarizing Customer Reviews [C]. In: Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2004: 168-177.
[5] Kim S M, Hovy E. Determining the Sentiment of Opinions [C]. In: Proceedings of the COLING, 2004: 1367-1373.
[6] Kobayashi N, Inui K, Matsumoto Y, et al. Collecting Evaluative Expressions for Opinion Extraction [A].//Natural Language Processing (IJCNLP 2004) [M]. Heidelberg, Berlin: Springer, 2005: 596-605.
[7] Bloom K, Garg N, Argamon S. Extracting Appraisal Expressions [C]. In: Proceedings of Human Language Technology Conferences of the North American Chapter of the Association of Computational Linguistics (HLT-NAACL). 2007: 308-315.
[8] Zhuang L, Jing F, Zhu X. Movie Review Mining and Summarization [C]. In: Proceedings of the 2006 ACM International Conference on Information and Knowledge Management, Arlington, Virginia, USA. ACM, 2006: 43-50.
[9] 娄德成, 姚天昉. 汉语句子语义极性分析和观点抽取方法的研究[J]. 计算机应用, 2006, 26(11): 2622-2625. (Lou Decheng, Yao Tianfang. Semantic Polarity Analysis and Opinion Mining on Chinese Review Sentences [J]. Computer Application, 2006, 26(11): 2622-2625.)
[10] 王素格, 吴苏红. 基于依存关系的旅游景点评论的特征-观点对抽取[J]. 中文信息学报, 2012, 26(3): 116-121. (Wang Suge, Wu Suhong. Feature-Opinion Extraction in Scenic Spots Reviews Based on Dependency Relation [J]. Journal of Chinese Information Processing, 2012, 26(3): 116-121.)
[11] 赵妍妍, 秦兵, 车万翔, 等. 基于句法路径的情感评价单元识别[J]. 软件学报, 2011, 22(5): 887-898. (Zhao Yanyan, Qin Bing, Che Wanxiang, et al. Appraisal Expression Recognition Based on Syntactic Path [J]. Journal of Software, 2011, 22(5): 887-898.)
[12] 陈炯, 张虎, 曹付元. 面向中文客户评论的评价搭配识别研究[J]. 计算机工程与设计, 2013, 34(3): 1073-1077. (Chen Jiong, Zhang Hu, Cao Fuyuan. Research on Identification of Evaluation Collocation from Chinese Customer Reviews [J]. Computer Engineering and Design, 2013, 34(3): 1073-1077.)
[13] 黄亿华, 濮小佳, 袁春风, 等. 基于句法树结构的情感评价单元抽取算法[J]. 计算机应用研究, 2011, 28(9): 3229-3234. (Huang Yihua, Pu Xiaojia, Yuan Chunfeng, et al. Appraisal Expression Extraction Based on Parse Tree Structure [J]. Application Research of Computers, 2011, 28(9): 3229-3234.)
[14] Che W, Li Z, Liu T. LTP: A Chinese Language Technology Platform [C]. In: Proceedings of the 23rd International Conference on Computational Linguistics -COLING, Beijing, China. 2010:13-16.
[15] NLPIR/ICTCLAS汉语分词系统[EB/OL]. [2014-07-19]. http:// ictclas.nlpir.org/. (NLPIR/ICTCLAS Chinese Segmentation System [EB/OL]. [2014-07-19]. http://ictclas.nlpir.org/.)

[1] Shen Zhuo,Li Yan. Mining User Reviews with PreLM-FT Fine-Grain Sentiment Analysis[J]. 数据分析与知识发现, 2020, 4(4): 63-71.
[2] Hui Nie. Modeling Users with Word Vector and Term-Graph Algorithm[J]. 数据分析与知识发现, 2019, 3(12): 30-40.
[3] Tang Xiaobo, Qiu Xin. Research on Subject-Oriented High Quality Reviews Mining Model[J]. 现代图书情报技术, 2015, 31(7-8): 104-112.
[4] Wang Yong, Zhang Qin, Yang Xiaojie. Research on the Method of Extracting Features from Chinese Product Reviews on the Internet[J]. 现代图书情报技术, 2013, (12): 70-73.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938   E-mail:jishu@mail.las.ac.cn