基于情感分析的企业产品级竞争对手识别研究——以用户评论为数据源

doi:10.13266/j.issn.0252-3116.2016.01.012

图书情报工作 ›› 2016, Vol. 60 ›› Issue (1): 83-90,97.DOI: 10.13266/j.issn.0252-3116.2016.01.012

基于情感分析的企业产品级竞争对手识别研究——以用户评论为数据源

肖璐¹, 陈果², 刘继云³

1. 南京大学信息管理学院南京 210023;
2. 南京理工大学经济管理学院南京 210094;
3. 东莞理工学院经济贸易系东莞 523808

收稿日期:2015-11-13 修回日期:2015-12-20 出版日期:2016-01-05 发布日期:2016-01-05
作者简介:肖璐(ORCID:0000-0001-5485-1407),博士后,E-mail:156300772@qq.com;陈果(ORCID:0000-0002-2222-7893),讲师,博士;刘继云(ORCID:0000-0001-9085-0794),教授,博士。
基金资助:
本文系广东省科技计划项目"高新区科技信息公共服务平台关键技术研究"(项目编号:2010A010100003)阶段性研究成果之一。

Study on Identification of Enterprise Product Level Competitor Based on Sentiment Analysis:Taking User Reviews for Data Resources

Xiao Lu¹, Chen Guo², Liu Jiyun³

1. School of Information Management, Nanjing University, Najing 210023;
2. School of Economics & Management, Nanjing University of Science and Technology, Najing 210094;
3. Department of Economy and Commerce, Donggun University of Technology, Dongguan 523808

Received:2015-11-13 Revised:2015-12-20 Online:2016-01-05 Published:2016-01-05

摘要/Abstract

摘要： [目的/意义]针对传统方法的不足,提出一种以用户评论为数据源的企业产品级竞争对手识别方法。[方法/过程]首先,根据企业分析维度确定候选竞争产品,进行相关评论文本采集;其次,利用信息抽取技术从本企业产品评论中抽取用户较为关注的产品特征;然后,基于情感分析技术设计特征情感权重算法;利用该算法对本企业产品特征进行优劣势分析,获取优势与劣势特征集,完成待分析产品向量空间表示与相似度计算;分析计算结果,挖掘出与本企业产品优势相似及劣势互补的候选竞争产品,并选择优势相似且劣势互补的产品为主要竞争对手,其他优势相似的产品为次要竞争对手。在实证部分,选择"红米Note"手机为分析对象,以"淘宝""京东""中关村在线"多源评论为数据源,利用基于情感分析的竞争对手识别方法挖掘该产品的主要和次要竞争对手。[结果/结论]本文的基于情感分析的竞争对手识别方法能够实现企业产品级竞争对手的识别与分析。

关键词: 竞争对手识别, 情感分析, 用户评论, 向量空间模型

Abstract: [Purpose/significance] For the lack of traditional methods, this paper presents an identification method for enterprise competitor based on user reviews.[Method/process] First of all, it chooses candidate competing products according to the analysis dimensions of enterprise, and grabs the relative reviews texts.Secondly, it extracts the product characteristics which users pay more attention from enterprise product reviews by information extracts technology, and designs a weight calculation algorithms of emotion features based on sentiment analysis technology.Thirdly, it analyzes the advantages and disadvantages of enterprise product characteristics by this algorithms, and then obtains the feature sets of advantages and disadvantages, to finish products vector space representation and similarity calculation.Finally, it digs up candidate competing products with similar advantage and complementary disadvantages to enterprise products according to the calculation results, and then chooses products with similar advantage and complementary disadvantages as the main competitors, and the other similar advantages products as the minor competitors.In the empirical part, it chooses "Red rice Note" phone as the analytic target, and uses the method which identifies competitor basecl on sentiment analysis to mine products of major and minor competitors based on the data from Taobao, Jingdong and ZOL.[Result/conclusion] This method can realize the identification and analysis of enterprise product level competitor.

Key words: identification of competitor, sentiment analysis, user review, vector space model

中图分类号:

G250

肖璐, 陈果, 刘继云. 基于情感分析的企业产品级竞争对手识别研究——以用户评论为数据源[J]. 图书情报工作, 2016, 60(1): 83-90,97.

Xiao Lu, Chen Guo, Liu Jiyun. Study on Identification of Enterprise Product Level Competitor Based on Sentiment Analysis:Taking User Reviews for Data Resources[J]. LIS, 2016, 60(1): 83-90,97.

参考文献

[1] 徐宏宇,张左之.中国企业竞争情报实施现状调查分析[J].图书情报工作,2010,54(2):82-86.
[2] 唐晓波,郭萍.基于语义文本挖掘的企业竞争对手分析模型研究[J].情报学报,2013,32(1):28-36.
[3] 王曰芬,甘利人.竞争对手的情报研究[J].情报理论与实践,2001,24(4):271-273.
[4] FRANCIS D B,SAWKA K A,HERRING J P.Competitors:who to watch,what to watch,who to ignore,and how to tell the difference[J].Competitive intelligence review,1995,6(3):41-46.
[5] 温金林,于英川.监视竞争对手——对竞争对手进行排序[J].情报学报,2001,20(5):598-603.
[6] 汪克夷,冯桂平.竞争对手分类和排序的灰关联聚类模型及其应用研究[J].情报学报,2007,26(5):752-757.
[7] De CHERNATONY L,DANIELS K,JOHNSON G.A cognitive perspective on managers' perceptions of competition[J].Journal of marketing management,1993,9(4):373-381.
[8] PORAC J F,THOMAS H.Taxonomic mental models in competitor definition[J].Academy of management review,1990,15(2):224-240.
[9] CLARK B H,MONTGOMERY D B.Managerial identification of competitors[J].The journal of marketing,1999,63(3):67-83.
[10] BERGEN M,PETERAF M A.Competitor identification and competitor analysis:a broad-based managerial approach[J].Managerial and decision economics,2002,23(4-5):157-169.
[11] 郑重.基于聚类分析的企业动态竞争对手辨识[J].情报杂志,2010,29(8):148-151.
[12] 吴晓伟,徐福缘,宋文官.社会关系态势图在竞争对手分析中的应用[J].情报学报,2007,26(1):100-105.
[13] HU M,LIU B.Mining and summarizing customer reviews[C]//Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining.New York:ACM,2004:168-177.
[14] HU M,LIU B.Mining opinion features in customer reviews[C]//Proceedings of the 19th national conference on Artifical Intelligence.Menlo Park:AAAI press,2004:755-760.
[15] POPESCU A M,ETZIONI O.Extracting product features and opinions from reviews[M]//Natural language processing and text mining.London:Springer,2007:9-28.
[16] WEI C P,CHEN Y M,YANG C S,et al.Understanding what concerns consumers:a semantic approach to product feature extraction from consumer reviews[J].Information systems and e-business management,2010,8(2):149-167.
[17] TURNEY P D.Thumbs up or thumbs down?:semantic orientation applied to unsupervised classification of reviews[C]//Proceedings of the 40th annual meeting on association for computational linguistics.Morristown ACL,2002:417-424.
[18] HU M,LIU B.Opinion extraction and summarization on the Web[C]//Proceedings of the 21st national conterence on Artifical Intelligence,Boston:AAAI press,2006:1621-1624.
[19] 丁晟春,文能,蒋婷,等.基于CRF模型的半监督学习迭代观点句识别研究[J].情报学报,2012,31(10):1071-1076.
[20] 赵洁,温润.基于新词扩充和特征选择的微博观点句识别方法[J].情报学报,2013,32(9):945-951.
[21] XU K,LIAO S S,LI J,et al.Mining comparative opinions from customer reviews for competitive intelligence[J].Decision support systems,2011,50(4):743-754.
[22] 黄晓斌,周珍妮.观点挖掘在竞争对手分析中的应用[J].情报资料工作,2010(5):89-93.
[23] 周珍妮,黄晓斌.网络用户评论在企业竞争情报研究中的应用[J].情报理论与实践,2012,35(5):15-20.
[24] 施国良,程楠楠.Web环境下产品评论挖掘在企业竞争情报中的应用[J].情报杂志,2011,30(11):10-14.
[25] 张玉峰,何超.基于Web评论挖掘的动态竞争情报分析研究(上)——问题分析与模型构建[J].情报理论与实践,2012,35(6):63-66.
[26] 伍星,何中市,黄永文.产品评论挖掘研究综述[J].计算机工程与应用,2008,44(36):37-41.
[27] 史伟,王洪伟,何绍义.基于语义的中文在线评论情感分析[J].情报学报,2013,32(8):860-867.
[28] 李实,叶强,李一军,等.挖掘中文网络客户评论的产品特征及情感倾向[J].计算机应用研究,2010,27(8):3016-3019.
[29] 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):142-152.
[30] YI J,NASUKAWA T,BUNESCU R,et al.Sentiment analyzer:extracting sentiments about a given topic using natural language processing techniques[C]//Data mining,2003.ICDM 2003.Third IEEE international conference on.Washington,DC:IEEE,2003:427-434.
[31] 杜嘉忠,徐健,刘颖.网络商品评论的特征-情感词本体构建与情感分析方法研究[J].现代图书情报技术,2014(5):74-82.
[32] 程明结.基于意见挖掘的网络口碑分析系统设计与实现[D].武汉:武汉大学,2010.5.
[33] RILOFF E,WIEBE J,WILSON T.Learning subjective nouns using extraction pattern bootstrapping[C]//Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003-Volume 4.Edmonton:ACL,2003:25-32.
[34] TURNEY P D,LITTMAN M L.Unsupervised learning of semantic orientation from a hundred-billion-word corpus[R].Technical report EBB-1094,National Research Council Canada,Institute for Information Technology,2002.
[35] 火车采集器产品介绍[EB/OL].[2015-12-05].http://www.locoy.com/product/Introduce/.
[36] ZHANG H P,YU H K,XIONG D Y,et al.HHMM-based Chinese lexical analyzer ICTCLAS[C]//Proceedings of the second SIGHAN workshop on Chinese language processing-Volume 17.Sapporo:ACM,2003:184-187.
[37] SPSS China[EB/OL].[2015-12-10].http://www.spss.com.cn/.

基于情感分析的企业产品级竞争对手识别研究——以用户评论为数据源

Study on Identification of Enterprise Product Level Competitor Based on Sentiment Analysis:Taking User Reviews for Data Resources

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	韦景竹, 操慧子, 张乐乐. 基于在线评论的公共文化云活动用户需求研究[J]. 图书情报工作, 2022, 66(9): 66-73.
[2]	马晓悦, 孙铭菲. 融合热点事件主题演化的民族文化扩散研究[J]. 图书情报工作, 2022, 66(3): 106-117.
[3]	马晓悦, 孟啸, 王镇, 刘益东. 网络突发事件中社交机器人情感的交互式影响机制研究[J]. 图书情报工作, 2021, 65(8): 74-84.
[4]	吴茵茵. 英美高校图书馆在线展览的主题和情感特征定量分析[J]. 图书情报工作, 2021, 65(20): 142-150.
[5]	谭芳, 杨阳, 卓伊玲, 徐健, 肖卓. 网络隐私争议事件中用户隐私关注及情感对比研究[J]. 图书情报工作, 2021, 65(2): 87-97.
[6]	池毛毛, 潘美钰, 王伟军. 共享住宿与酒店用户评论文本的跨平台比较研究:基于LDA的主题社会网络和情感分析[J]. 图书情报工作, 2021, 65(2): 107-116.
[7]	蔡庆平, 马海群. 基于Word2Vec和CNN的产品评论细粒度情感分析模型[J]. 图书情报工作, 2020, 64(6): 49-58.
[8]	聂卉, 首欢容. 基于修正点互信息的特征级情感词极性自动研判[J]. 图书情报工作, 2020, 64(5): 114-123.
[9]	孔婧媛, 滕广青, 王思茗, 庹锐. 舆情当事人回应对网民情感的影响研究[J]. 图书情报工作, 2020, 64(18): 89-96.
[10]	梁甜, 彭国超, 邢飞. 我国智慧城市APP应用现状及问题分析[J]. 图书情报工作, 2019, 63(8): 65-73.
[11]	毕达天, 王福. 移动图书馆场景化信息接受过程的情感变化研究[J]. 图书情报工作, 2019, 63(6): 20-28.
[12]	张海涛, 刘雅姝, 张枭慧, 宋拓. 基于模块度的话题发现及网民情感波动研究——以新浪微博“中美间贸易摩擦”话题为例[J]. 图书情报工作, 2019, 63(4): 6-14.
[13]	余传明, 原赛, 王峰, 安璐. 大数据环境下文本情感分析算法的规模适配研究:以Twitter为数据源[J]. 图书情报工作, 2019, 63(4): 101-111.
[14]	尹丽春, 王悦. 基于在线评论的图书消费者满意度影响因素与作用机理[J]. 图书情报工作, 2019, 63(22): 106-117.
[15]	赵常煜, 吴亚平, 王继民. “一带一路”倡议下的Twitter文本主题挖掘和情感分析[J]. 图书情报工作, 2019, 63(19): 119-127.