Research of Chinese Chunk Parsing in Application of the Product Feature Extraction
Du Siqi1, Li Honglian1, Lv Xueqiang2
1 School of Information and Communication Engineering, Beijing Information Science and Technology University, Beijing 100101, China;
2 Beijing Key Laboratory of Internet Culture and Digital Dissemination Research, Beijing Information Science and Technology University, Beijing 100101, China
[Objective] This paper aims at the problem of product feature extraction, especially the noun phrase identification. [Methods] Chinese Chunk Parsing is used to extract the feature, and frequent sets are generated by Apriori. Then the candidate product features are filtered according to the rules of the minimum support, frequent nouns and TF-IDF. At last, the final product feature sets are obtained. [Results] In order to verify the effectiveness of the method, the car reviews are used in this paper, the average recall rate reaches 76.89%, the average precision rate reaches 84.03%. [Limitations] The recall rate is low and there is noun phrase identification error in the test. [Conclusions] Experiment results show that the method can extract product feature from Chinese reviews with good effects.
杜思奇, 李红莲, 吕学强. 汉语组块分析在产品特征提取中的应用研究[J]. 现代图书情报技术, 2015, 31(9): 26-30.
Du Siqi, Li Honglian, Lv Xueqiang. Research of Chinese Chunk Parsing in Application of the Product Feature Extraction. New Technology of Library and Information Service, 2015, 31(9): 26-30.
[1] 祁志民, 刘涌. 浅谈我国电子商务的发展现状与趋势[J]. 学术交流, 2009(7): 136-138. (Qi Zhimin, Liu Yong. Introduction to the China Electronic Commerce Development Present Situation and Trends [J]. Academic Exchange, 2009(7): 136-138.)
[2] 姚天昉, 聂青阳, 李建超, 等. 一个用于汉语汽车评论的意见挖掘系统[C]. 见: 中文信息处理前沿进展——中国中文信息学会二十五周年学术会议论文集. 2006. (Yao Tianfang, Nie Qingyang, Li Jianchao, et al. An Opinion Mining System for Chinese Automobile Reviews [C]. In: Proceedings of the 25th Academic Conference of Chinese Information Processing Society of China on Frontiers of Chinese Information Processing. 2006.)
[3] 娄德成, 姚天昉. 汉语句子语义极性分析和观点挖掘抽取方法的研究[J]. 计算机应用, 2006, 26(11): 2622-2625. (Lou Decheng, Yao Tianfang. Semantic Polarity Analysis and Opinion Mining on Chinese Reviews Sentence [J]. Computer Applications, 2006, 26(11): 2622-2625.)
[4] Shi B, Chang K. Mining Chinese Reviews [C]. In: Proceedings of the 6th IEEE International Conference on Data Mining Workshops. IEEE, 2006: 585-589.
[5] 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.
[6] Popescu A M, Etzioni O. Extracting Product Features and Opinions from Reviews [A].//Natural Language Processing and Text Mining [M]. Springer London, 2005: 339-446.
[7] 伍星, 何中市, 黄永文.基于弱监督学习的产品特征抽取[J]. 计算机工程, 2009, 35(13): 199-201. (Wu Xing, He Zhongshi, Huang Yongwen. Product Feature Extraction Based on Weakly Supervised Learning [J]. Computer Enineering, 2009, 35(13): 199-201.)
[8] 李实, 叶强, 李一军, 等. 中文网络客户评论的产品特征挖掘方法研究[J]. 管理科学学报, 2009, 12(2): 142-150. (Li Shi, Ye Qiang, Li Yijun, et al. Mining Features of Product from Chinese Customer Online Reviews [J]. Journal of Management Science in China, 2009, 12(2): 142-150.)
[9] 李业刚, 黄河燕. 汉语组块分析综述[J]. 中文信息学报, 2013, 27(3): 1-8. (Li Yegang, Huang Heyan. A Survey on
Chinese Chunk Parsing [J]. Journal of Chinese Information Process, 2013, 27(3): 1-8.)
[10] 周雅倩, 郭以昆, 黄萱菁, 等.基于最大熵方法的中英文基本名词短语识别[J]. 计算机研究与发展, 2003, 40(3): 440-445. (Zhou Yaqian, Guo Yikun, Huang Xuanjing, et al. Chinese and English BaseNP Recognition Based on a Maximun Entropy Model [J]. Journal of Computer Research and Development, 2003, 40(3): 440-445.)
[11] 路永和, 李焰锋. 改进TF-IDF算法的文本特征项权值计算方法[J]. 图书情报工作, 2013, 57(3): 90-95. (Lu Yonghe, Li Yanfeng. Improvement of Text Feature Weighting Method Based on TF-IDF Algorithm [J]. Library and Information Service, 2013, 57(3): 90-95.)
[12] 覃世安, 李法运. 文本分类中TF-IDF方法的改进研究[J]. 现代图书情报技术, 2013 (10): 27-30. (Qin Shian, Li Fayun. Improved TF-IDF Method in Text Classification [J]. New Technology of Library and Information Service, 2013(10): 27-30.)