B2C购物网站商品评价的效应研究
|
摘要
随着互联网和通信技术的发展与应用的不断深化，以互联网为平台的信息传播凸显出其对经济和社会巨大的影响力。网络购物用户购买商品以后对商品发表的在线评价信息作为在线口碑的一种表现形式，正在深刻改变着潜在网络购物用户的购买等经济行为模式、企业的销售能力和盈利性能以及其市场策略和行业竞争力。尽管我国电子商务环境的发展十分快速，学术界对在线评价信息这种新兴的信息媒体如何反应网络购物用户的网络购物行为规律以及其怎样影响商品的销售量等问题的研究还处于初始阶段。因此，研究在线评价信息对网络购物用户参考已经存在的在线评价信息提高购买决策的效率、电子商务销售企业提高对在线评价信息的管理、提高网络销售企业对网络购物用户行为活动的掌握从而制定更具竞争力的管理策略和营销策略，最终推动电子商务行业实现更大的盈利和健康发展具有现实意义与价值。
本论文以B2C购物网站的网络购物行业为研究背景，以京东商城为研究对象，借助网页信息抓取工具历经一个多月从京东商城抓取了30款手机的213516条在线评价信息23482条咨询信息，通过对这些信息进行处理和量化以后形成了不含时间的横截面数据和包含时间因素的面板数据。研究中以行为导向为研究范式，结合定性和定量分析。本研究的主要内容从以下三个方面进行：首先从网络购物用户的咨询、购买及评价行为出发分析了网络购物用户的在线活动的规律；其次通过因子分析找出网络购物用户购买商品之前对购物商场和商品的关注焦点以及购买商品之后发表在线评价时对商品的关注焦点；最后使用回归分析在线评价信息对商品销售数量的影响。
本研究使用的主要方法包括：比较分析法、关联规则挖掘法、因子分析法、最小二乘法、固定效应模型法和广义矩估计法。使用的主要工具分为数据抓取处理工具和数据分析工具两类。数据抓取处理数据为MetaSeeker、谷歌Xml文件合并工具、中科院的分词工具和牛津大学出版社的词频统计工具。数据分析工具为Excel函数、Spss16.0和Stata.
本研究的主要结论如下：
1.网络购物用户的数量和消费能力与网络购物消费者所在省（市）的经济发展水平有正向相关关系。
2.每周“星期二”和“星期三”是网络购物用户进行网络购物相关活动的高峰日期，每周“星期六”和“星期日”是网络购物用户进行网络购物相关活动的低峰日期。
3.每天的“下午”和“晚上”时间段是网络购物用户进行网络购物相关活动的高峰时间段，“凌晨”时间段是网络购物用户进行网络购物活动的低峰时间段。
4.网络购物用户咨询与购买行为之间没有必然联系，进行咨询活动的用户不一定购买商品，购买了商品的用户不一定在购买之前进行咨询活动。
5.网络购物用户购买与评价行为之间的日期差与消费者本身的特征和行为习惯有关。
6.手机购物用户购物之前进行咨询时主要关注商品价格、商城的支付、物流、售后服务、商品性能和产品规格，购物以后进行在线评价活动时主要关注手机的基本功能、是否是国产品牌以及手机信号的稳定性。
7.京东商城手机销售数量与商家制定的手机销售价格存在显著负相关关系，与在线评价信息的有用数和评价效价存在显著正相关关系。手机销售数量与手机的上市时间长短没有明显关系，与在线咨询数量没有显著关系。
8.国产品牌手机消费者受口碑效应的影响比非国产品牌手机消费者明显，非国产品牌手机的消费者受从众效应的影响比国产品牌手机消费者明显。
本文立足于网络购物用户群体层面，分析了网络购物用户群体的网络购物行为规律，分析销售数量的影响因素，给网络商城和销售企业提供了消费者的行为规律和销售量的影响因素，并提出了合理的建议，有利于提高网络商城和企业的竞争力，有着比较重要的现实意义。
With the development and application of Internet and communication technology,Internet information dissemination convex platform shows its great influence on theeconomic and society. The online review information published by the onlineconsummers as a form of online word-of-mouth, is profoundly changing the potential ofonline consummers’ buy and other economic behavior, and its ability of sales and profitperformance and its market strategies and industry competitiveness. Although thedevelopment of China's e-commerce environment is very fast, research on how reviewinformation as the newly information media reaction of online shopping behavior ofonline consummers and how to influence the sales, is still in the initial stage. Therefore,online review information as online consumers’ reference already exists to improve theefficiency of their purchasing decision, improve the online enterprise’s reviewinformation management, improve the network marketing enterprises to grasp the onlineconsumers’ activity rules and make more competitive strategy and marketing strategy,and ultimately to promote the electronic commerce industry to achieve greaterprofitability and healthy development.
In this thesis, online shopping industry of B2C shopping website as theresearch background, the Jingdong Mall as the research object, by means of Webpageinformation capture tool after more than a month from Jingdong mall we grabbed213516online review information and23482consult information of30mobile phones, theformation of cross section data does not contain time factor and panel data includes atime factor through after the information is processed and quantized. Take action orientedresearch paradigm in the research, combining with qualitative and quantitative analysis.The main content of this study from the following three aspects: firstly, evaluation ofbehavior of consummers’ online activity regulations analysis from the onlineconsummers’ consulting and review information; secondly,finding out the onlineconsummers’ foucus before buying and after buying activity; finally, anylyze the factorsthat affect the sales with the method of regression analysis.
The main research methods used in this thesis includes: comparative analysis,association rule mining method, factor analysis method, least square method, the fixedeffect model and generalized method of moments estimators. The main tools usedincludes tow kinds:data capture&processing tools and data analysis tools.Data capture &processing tools includes: MetaSeeker, Google Xml file merge tool, the ChineseAcademy of Sciences segmentation tool and University of Oxford press tool. Dataanalysis tools used in the research includes Excel, Spss16.0and Stata.
The major findings are as follows:
1. There is positive correlation between the number&consumption ability ofonline consumers and the level of economic development of the consumers’ province(city).
2."Tuesday" and "Wednesday" is the high peak date for the online shoppingactivities,"Saturday" and "Sunday" is the low peak date of the online shopping activities.
3. Every "afternoon" and "Nights" time period is the peak period of onlineshopping related activities,"dawn" time period is the low peak period of online shoppingactivities.
4. There is no necessary connection between the consultation and purchasebehaviors, the users with consulting activity doesn't have to buy goods, users who buygoods are not necessarily to consult before buying.
5. Purchasing behavior and reviewing date difference is related to the habits andbehavior of the online consumers.
6. Mobile phone consumers consult for advice before shopping mainly focus oncommodity prices, payment, logistics, customer service center service, productperformance and product specifications;when review after perchasing they mainly focuson stability of basic function, domestic brands or not and the mobile phone signal.
7. There is a significant negative correlation between the number of mobilephone Jingdong Mall sales and mobile phone prices, there is a significant positivecorrelation between the number of sales and online reviews and assessment and usefulinformation. No obvious relationship between the mobile phone sales and the length oftime of mobile phone published, and no significant relationship with the number of onlineconsulting.
8. Domestic brand mobile phone consumers are more affected by word-of-moutheffect than the none domestic mobile phone brand consumers clearly, the effects of nondomestic brand mobile phone consumers are more affected by conformity effect thandomestic brand mobile phone consumers.
This paper is based on the online consumer groups, analyzes the online shopping
behavior of the online consumer groups, analysis of the factors affecting the quantity ofsales, provides the factors affecting the behavior of consumers and sales to Internetshopping and sales enterprise, and give the forward reasonable suggestion, help toimprove the competitiveness of enterprises, has very important practical significance.
本论文以B2C购物网站的网络购物行业为研究背景，以京东商城为研究对象，借助网页信息抓取工具历经一个多月从京东商城抓取了30款手机的213516条在线评价信息23482条咨询信息，通过对这些信息进行处理和量化以后形成了不含时间的横截面数据和包含时间因素的面板数据。研究中以行为导向为研究范式，结合定性和定量分析。本研究的主要内容从以下三个方面进行：首先从网络购物用户的咨询、购买及评价行为出发分析了网络购物用户的在线活动的规律；其次通过因子分析找出网络购物用户购买商品之前对购物商场和商品的关注焦点以及购买商品之后发表在线评价时对商品的关注焦点；最后使用回归分析在线评价信息对商品销售数量的影响。
本研究使用的主要方法包括：比较分析法、关联规则挖掘法、因子分析法、最小二乘法、固定效应模型法和广义矩估计法。使用的主要工具分为数据抓取处理工具和数据分析工具两类。数据抓取处理数据为MetaSeeker、谷歌Xml文件合并工具、中科院的分词工具和牛津大学出版社的词频统计工具。数据分析工具为Excel函数、Spss16.0和Stata.
本研究的主要结论如下：
1.网络购物用户的数量和消费能力与网络购物消费者所在省（市）的经济发展水平有正向相关关系。
2.每周“星期二”和“星期三”是网络购物用户进行网络购物相关活动的高峰日期，每周“星期六”和“星期日”是网络购物用户进行网络购物相关活动的低峰日期。
3.每天的“下午”和“晚上”时间段是网络购物用户进行网络购物相关活动的高峰时间段，“凌晨”时间段是网络购物用户进行网络购物活动的低峰时间段。
4.网络购物用户咨询与购买行为之间没有必然联系，进行咨询活动的用户不一定购买商品，购买了商品的用户不一定在购买之前进行咨询活动。
5.网络购物用户购买与评价行为之间的日期差与消费者本身的特征和行为习惯有关。
6.手机购物用户购物之前进行咨询时主要关注商品价格、商城的支付、物流、售后服务、商品性能和产品规格，购物以后进行在线评价活动时主要关注手机的基本功能、是否是国产品牌以及手机信号的稳定性。
7.京东商城手机销售数量与商家制定的手机销售价格存在显著负相关关系，与在线评价信息的有用数和评价效价存在显著正相关关系。手机销售数量与手机的上市时间长短没有明显关系，与在线咨询数量没有显著关系。
8.国产品牌手机消费者受口碑效应的影响比非国产品牌手机消费者明显，非国产品牌手机的消费者受从众效应的影响比国产品牌手机消费者明显。
本文立足于网络购物用户群体层面，分析了网络购物用户群体的网络购物行为规律，分析销售数量的影响因素，给网络商城和销售企业提供了消费者的行为规律和销售量的影响因素，并提出了合理的建议，有利于提高网络商城和企业的竞争力，有着比较重要的现实意义。
With the development and application of Internet and communication technology,Internet information dissemination convex platform shows its great influence on theeconomic and society. The online review information published by the onlineconsummers as a form of online word-of-mouth, is profoundly changing the potential ofonline consummers’ buy and other economic behavior, and its ability of sales and profitperformance and its market strategies and industry competitiveness. Although thedevelopment of China's e-commerce environment is very fast, research on how reviewinformation as the newly information media reaction of online shopping behavior ofonline consummers and how to influence the sales, is still in the initial stage. Therefore,online review information as online consumers’ reference already exists to improve theefficiency of their purchasing decision, improve the online enterprise’s reviewinformation management, improve the network marketing enterprises to grasp the onlineconsumers’ activity rules and make more competitive strategy and marketing strategy,and ultimately to promote the electronic commerce industry to achieve greaterprofitability and healthy development.
In this thesis, online shopping industry of B2C shopping website as theresearch background, the Jingdong Mall as the research object, by means of Webpageinformation capture tool after more than a month from Jingdong mall we grabbed213516online review information and23482consult information of30mobile phones, theformation of cross section data does not contain time factor and panel data includes atime factor through after the information is processed and quantized. Take action orientedresearch paradigm in the research, combining with qualitative and quantitative analysis.The main content of this study from the following three aspects: firstly, evaluation ofbehavior of consummers’ online activity regulations analysis from the onlineconsummers’ consulting and review information; secondly,finding out the onlineconsummers’ foucus before buying and after buying activity; finally, anylyze the factorsthat affect the sales with the method of regression analysis.
The main research methods used in this thesis includes: comparative analysis,association rule mining method, factor analysis method, least square method, the fixedeffect model and generalized method of moments estimators. The main tools usedincludes tow kinds:data capture&processing tools and data analysis tools.Data capture &processing tools includes: MetaSeeker, Google Xml file merge tool, the ChineseAcademy of Sciences segmentation tool and University of Oxford press tool. Dataanalysis tools used in the research includes Excel, Spss16.0and Stata.
The major findings are as follows:
1. There is positive correlation between the number&consumption ability ofonline consumers and the level of economic development of the consumers’ province(city).
2."Tuesday" and "Wednesday" is the high peak date for the online shoppingactivities,"Saturday" and "Sunday" is the low peak date of the online shopping activities.
3. Every "afternoon" and "Nights" time period is the peak period of onlineshopping related activities,"dawn" time period is the low peak period of online shoppingactivities.
4. There is no necessary connection between the consultation and purchasebehaviors, the users with consulting activity doesn't have to buy goods, users who buygoods are not necessarily to consult before buying.
5. Purchasing behavior and reviewing date difference is related to the habits andbehavior of the online consumers.
6. Mobile phone consumers consult for advice before shopping mainly focus oncommodity prices, payment, logistics, customer service center service, productperformance and product specifications;when review after perchasing they mainly focuson stability of basic function, domestic brands or not and the mobile phone signal.
7. There is a significant negative correlation between the number of mobilephone Jingdong Mall sales and mobile phone prices, there is a significant positivecorrelation between the number of sales and online reviews and assessment and usefulinformation. No obvious relationship between the mobile phone sales and the length oftime of mobile phone published, and no significant relationship with the number of onlineconsulting.
8. Domestic brand mobile phone consumers are more affected by word-of-moutheffect than the none domestic mobile phone brand consumers clearly, the effects of nondomestic brand mobile phone consumers are more affected by conformity effect thandomestic brand mobile phone consumers.
This paper is based on the online consumer groups, analyzes the online shopping
behavior of the online consumer groups, analysis of the factors affecting the quantity ofsales, provides the factors affecting the behavior of consumers and sales to Internetshopping and sales enterprise, and give the forward reasonable suggestion, help toimprove the competitiveness of enterprises, has very important practical significance.
引文
[1]张海燕．基于分词的中文文本自动分类研究与实现［Ｄ］．长沙：湖南大学，2002.
[2]娄德成．基于ＮＬＰ技术的中文网络评论观点抽取方法的研究［Ｄ］．上海：上海交通大学，2007.
[3]郝媛媛，叶强，李一军．基于影评数据的在线评论有用性影响因素研究[J]．管理科学学报，2010年第13卷第8期，78-96页．
[4]施国良，石桥峰.基于文本挖掘的不同购物网站商品评论一致性研究[J].现代图书情报技术，2011年第12期，64-68页.
[5]李健.在线商品评论对产品销量影响研究[J].现代情报，2012年第1期，164-167页.
[6]王琦，唐世渭，杨冬青,等.基于DOM的网页主题信息自动提取[J].计算机研究与发展，2004年第41卷第10期，1786-1792页.
[7] CNNIC.2012年中国网民消费行为调查报告.
[8] CNNIC.第31次中国互联网络发展状况统计报告.
[9]埃弗瑞姆.特伯恩（Efrain Turban）、戴维.金（David King）著，电子商务导论（Introduction of Electronic Business），人民大学出版社，2010年第一版。
[10]罗敖生.基于ASP实现网上数据的自动抓取[J].江苏广播电视大学学报，2002年第13卷第6期，59-61页.
[11]朱晓静，方磊坤，李太君.基于P2P网络的信息检索[J].现代电子技术，2007年第4期，120-122页.
[12]顾潇华，郭军城.网页超链抓取及自动分类技术实现[J].河北大学学报（自然科学版），2007年第1期，99-102页.
[13] YU D, SHEIKHOLESLAMI G, ZHANGA. Findout: finding outliers in largedatasets[J]. Knowledge and Information Systems,2002年第4卷第4期，387-412页.
[14]张博，蔡皖东.面向主题的网络蜘蛛技术研究及系统实现[J].微电子学与计算机2009年第5期，52-55页.
[15]袁浩，黄烟波.网页标题分析对主题爬虫的改进[J].计算机技术与发展，2009年第6期，22-28页.
[16]白鹤，汤迪斌，王劲林.分布式多主题网络爬虫系统的研究与实现[J].计算机工程，2009年第35卷第19期，13-19页.
[17]郭会斌.营销口碑的产生路径与创造研究[J].经济与管理.2005年第19卷第l1期，44-46页.
[18]阙克儒.网络匿名性、企业形象与关系品质对网络口碑影响之研究--以线上游戏为例[D].中兴大学,2004.
[19]黄英,朱顺德.二十一世纪的口碑营销及其在中国的发展潜力[J].管理前沿.2003年第6期，33-36页.
[20]郝媛媛.在线评论对消费者感知与购买行为影响的实证研究[D].黑龙江：哈尔滨工业大学，2010.
[21]章晶晶.网络环境下口碑再传播意愿的影响因素研究[D].浙江：浙江大学,2007.
[22]卢向华、冯越.网络口碑的价值——基于在线餐馆点评的实证研究[J].管理世界,2009年第7期，126-132,171页.
[23]周晶晶.在线客户评论对消费者购买决策的影响力研究[D].浙江：浙江大学，2010.
[24]张素华.基于网络外部性与从众效应的锁定策略研究[D].福建：厦门大学，2008.
[25]殷国鹏.消费者认为怎样的在线评论更有用？[J].管理世界，2012年第12期，115-124页。
[26]姜巍，张莉，戴翼，蒋竞和王刚.面向用户需求获取的在线评论有用性分析[J].计算机学报，2013年第1期，121-131页.
[27]杨爽，徐畅.在线产品评论有用性的影响机制[J].求索，2013年第3期，249-251页.
[28]郝媛媛、邹鹏、李一军、叶强.基于电影面板数据的在线评论情感倾向对销售收入影响的实证研究[J].管理评论，2009年第10期，95-103页.
[29]李宏，喻葵，夏景波.负面在线评论对消费者网络购买决策的影响一个实验研究[J].情报杂志，2011年第5期，202-207页.
[30]孟美任，丁晟春.在线中文商品评论可信度研究[J].现代图书情报技术，2013年第9期，60-66页。
[31]李念武，岳蓉.网络口碑可信度及其对购买行为之影响的实证研究[J].图书情报工作，2009第53卷第22期，133-137页.
[32]施国良石桥峰.基于文本挖掘的不同购物网站商品评论一致性研究[J].现代图书情报技术,2011年第12期，64-68页.
[33]潘勇，赵军民.基于顾客满意度的B2C电子商务网站评价[J].现代情报，2008第5期，220-223页.
[34]李思曼，王宇航，李亚平.基于顾客满意的消费者网上购物影响因素分析[J].商业研究，2009第01期，203-206页.
[35]饶曦.网络购物中的消费者购买行为分析[J].现代企业,2010第6期，50-51,57页.
[36]王秀丽田祯祎.网民网络购物行为调查[J].图书情报工作,2011第6期，20-23,95页.
[37]马庆国.管理统计：数据获取、统计原理、SPSS工具应用与研究，科学出版社，2002.08.01.
[38]陈胜可.SPSS统计分析从入门到精通，清华大学出版社，2013.05，第二版.
[39]吴明隆，涂金堂.SPSS与统计应用分析，东北财经大学出版社，2012年9月第一版。
[40]杨维忠，张甜.SPSS统计分析与行业应用案例详解，清华大学出版社，2013年3月第二版。
[41]朱建平，方匡南，章贵军.SPSS统计分析与应用，首都经济贸易大学出版社，2013年2月第一版。
[42] Zhang Z．Weighing stars：Aggregating online product reviews forintelligent e—commerce applications[J]．IEEE Intelligent Systems，Vol.23(5)：PP42—49．,2008.
[43] Tsai F S, Kwee A T. Database Optimization for Novelty Mining of BusinessBlogs [J]. Expert Systems With Applications, Vol.38(9):PP11040-11047.,2011.
[44] Liu Y，Huang X J，An A J，et a1．Modeling and predicting the helpfulnessof online reviews[C].Procedings of the8thIEEE International Conference onData Mining，Washington．DC，USA：IEEE Computer Society：PP443—452．，2008.
[45] Ghose A，Ipeiortis P G．Designing novel review ranking systems：Predictingthe usefulness and impact of reviews[C].Proceedings of the9th ACM Conferenceon Electronic Commerce，Minneapolis， MN，USA：Association for ComputingMachincry：PP303—310．，2007.
[46] Otterbacher J．”Helpfulness”in online communities：A measure of messagequality[C].Proceedings of the27International Conference on Human Factorsin Computing Systems，Boston，MA，USA：Association for Computing Machinery：PP955—964．，2009.
[47] Ye Q，Zhang Z Q，Law R．Sentiment classification of online reviews totravel destinations by supervised machine learning approaches[J]．ExpertSystems with Applications，Vol.36(3)：PP6527—6535.,2009.
[48] Abbasi A，Chen H C，Salem A．Sentiment analysis in multiple languages：Feature selection for opinion classification in web forums[J]． ACMTransactions on Information Systems，Vol.26(3)：PP1—34．,2008.
[49] Abbasi A，Chen H C，Thoms S，et a1．Affect analysis of web forums andblogs using correlation ensembles[J]．IEEE Transactions on Knowledge and DataEngineering，Vol.20(9)：PP1168—1180.,2008.
[50] Kim S M，Pantel P，Chklovski T，et a1．Automatically assessing reviewhelpfulness[C]Proceedings of the Conference Empirical Methods in NatualLanguage Processing，Morristown，NJ，USA：Association for ComputationalLinguistics：PP423—430．，2006.
[51] Chen C C，Tseng Y D．Quality evaluation of product reviews using aninformation quality framework[J]．Decision Support Systems，Vol.50(4)：PP755—768．,2011.
[52] Li N, Wu D D. Using Text Mining and Sentiment Analysis for On Line ForumsHotspot Detection and Forecast [J]. Decision Support Systems,Vol.48(2):PP354-368.,2010.
[53] Chang C W, Lin C T, Wang L Q. Mining the Text Information to Optimizingthe Customer Relationship Management[J]. Expert Systems with Applications,Vol.36(2):PP1433-1443.,2009.
[54] Xu K, Liao S S, Li J, et al. Mining Comparative Opinions from CustomerReviews for Competitive Intelligence[J]. Decision Support Systems,Vol.50(4): PP743-754.,2010.
[55] Gamon M．Sentiment classification on customer feedback data：Noisydata，large feature vectors，and the role of linguistic analysis[C] Proceedingof COLING-04， the20th International Conference on ComputationalLinguistics，Geneva，USA COLING， PP841—847．,2004.
[56] Hu N，Pavlou P A，Zhang J．Overcoming the J-shaped distribution of productreviews [J]．Communications of the ACM，Vol.52(10)：PP144—147．，2009.
[57] Jiang Z H，Benbasat I．Virtual product experience：Effects of visualand functional control of products on perceived diagnosticity and flow inelectronic shopping[J]．Journal of Management Information Systems，Vol.21(3)：PP111—147．,2004。
[58] Jiang Z H，Benbasat I．Investigating the irfluence of the functionalmechanisms of online product presentations[J]．Information Systems Research，Vol.18(4)：PP454—470．,2007.
[59] Pavlou P A，Fygenson M．Understanding and predicting electronic commerceadoption：An extension of the theory of planned behavior[J]．MIS Quarterly，Vol.30(1)：PP115—143．,2006.
[60] Pavlou P A，Liang H G，Xue Y J．Understanding and mitigating uncertaintyin online exchange relationships：A principal—agent perspective[J]．MISQuarterly，Vol.31(1)：PP105—136．,2007.
[61] Kotler P，Keller K．Marketing Management[M]．12ed．，Upper saddle River，NJ：Prentice—Hall，2005．
[62] Kohli R，Devar S，Mahmood M A．Understanding determinants of onlineconsumer satisfaction： A decision process perspective[J]． Journal ofManagement Information Systems，Vol.21(1)：PP115—135．,2004.
[63] Mudambi S M．Schuf D．What makes a helpful online review? A study ofcustomer reviews on Amazon．Com，MIS Quarterly，Vol.34(1)：PP185—200．,2010.
[64] Hevner A R，March S T，Park J，et a1．Design science in information systemsresearch[J]．MIS Quarterly，Vol.28(1)：PP75—105．,2004.
[65] Walls J G，Widmeyer G R，Sawy A E．Building an information system designtheory for vigilant EIS[J]．Information Systems Research，Vol.3(1)：PP36—59．,1992.
[66] March S T，Simith G F．Design and natural—science research on informationtechnology[J]．Decision Support System，Vol.15(4)：PP251—266．,1995.
[67] March S T，Storey V C．Design science in the information systemsdeccipline： An introduction to the special issue on design scienceresearch[J]．MIS Quarterly，32(4)：PP725—730．,2008.
[68] Stigle G J．The econnomics of information[J]．Journal of PoliticalEconomy，Vol.69(3)：PP213—225．,1961.
[69] Chen Y B，Xie J H．Online consumer review：Word-of-mouth as a news elementof marketing communication mix[J]．Management Science，Vol.54(3)：PP477—491．,2008.
[70] Lee T，Bradlow E．Automatic Construction of Conjoint Attributes andLevels from Online Customer Reviews[R]．Florida Decision and InformationSciences Workshop，2007.
[71] Liu J J, Cao Y B, Lin C Y, et al. Low-quality product review detectionin opinion summarization[C].Proceedings of the Joint Conference on EmpiricalMethods in Natural Language Processing and Computational Natural LanguageLearning(EMNLP-CoNLL),Prague: Association Linguistics:PP334-342.,2007.
[72] Emanuel Rosen, Roger E.Scholl.The Anatomy of Buzz: How to CreateWord-of-Mouth Marketing[M]. New York: Random House:PP44-47.,2000.
[73] Blackwell, Roged D., Paul W.Miniard and James F.Engle. ConsumerBehavior[M]. NewYork: Harcount, Inc,2001.9.
[74] Christiansen T., Tax S. S. Measuring word of mouth: the questions ofwho and when?[J]. Journal of Marketing Communications.6(3):185-199.,2000.
[75] Dellaroeas, C. The digitization of word of mouth: Promise and challengesof online feedback mechanisms[J].Management Science. Vol.49(10):PP1407-1424.,2003.
[76] Hennig Thurau, K. P. Gwinner, G. Walsh. D. D. Gremler. Electronicword-of-mouth via consumer-opinion platforms: What motivates consumers toarticulate themselves on the Internet?[J]. Journal of Interactive Marketing.Vol.18(1):PP38-52.2004.
[77] Datta, P. R.，Chowdhury, D. N. and Chakraborty, B. R. Viral marketing:new form of word-of-mouth through Internet [J]. The Business Review,Vol.3(2):PP69-75.,2005.
[78] Katz, E., Lazarsfeld P. F. Personal Influence: The Part Played by Peoplein the Flow of Mass Communication[M]. New York: The Free Press,1964.
[79] Leibenstein, H. Bandwagon, snob, and Veblen. Effeets in the Theory ofConsumers’ Demand [J].The Quarterly Journal of Eeonomies,Vol.64(2):PP183-207.,1950.
[80] Lascu D-N.,Zinkhan G.Consumer Conformity:Review and Applications forMarketing Theory and Practice[J].Jounal of Marketing Theory&Practie.Vol.7(3):PPl-12.,1999.
[81] Banerjee,A.V.A Simple Model of Herd Behavior[J].Quarterly Jounal ofEconomics,Vol.107(3):PP797一817.,1992.
[82] Soo-Min Kim, Patrick Pantel, Tim Chklovski and Marco Pennacchiotti.Automatically Assessing Review Helpfulness [C]. Proceedings of the2006Conference on Empirical Methods in Natural Language Processing,EMNLP:PP423-430.,2006.
[83] Yuanyuan Hao, Qiang Ye, YiJun Li and Zhuo Cheng.How does the Valenceof Online Consumer Reviews Matter in Consumer Decision Making? Differencesbetween Search Goods and Experience Goods[C]. Proceedings of the43rd HawaiiInternational Conference on System Sciences,2010.
[84] Do-Hyung Park and Sara Kim. The effects of consumer knowledge on messageprocessing of electronic word-of-mouth via online consumer reviews[J].Electronic Commerce Research and Applications,(Vol.7): PP399–410.,2008.
[85] Jumin Leea,Park D H, Han I.The effect of negative online consumerreviews on product attitude: An information processing view[J].ElectronicCommerce Research and Applications,(Vol.7):PP341-352.,2008.
[86] Wenjing Duana, Bin Gub, Andrew B. Whinston. The dynamics of onlineword-of-mouth and product sales—An empirical investigation of the movieindustry[J].Journal of Retailing,(Vol.84):PP233-242.,2008.
[87] Garrett P. Sonnier, Leigh McAlister. A Dynamic Model of the Effect ofOnline Communications on Firm Sales. Marketing Science, Vol.30,No.4: PP702-716.,2011.
[88] Judith A. Chevalier and Dina Mayzlin.The Effect of Word of Mouth on Sales:Online Book Reviews[J].Journal of Marketing Research, Vol.43,No.3:PP345-354.,2006.
[89] Qiang Ye, Rob Law, Bin Gu. The impact of online user reviews on hotelroom sales[J]. International Journal of Hospitality Management,Vol.28:PP180-182.,2009.
[90] Xia Liu，Mengqiao He， Fang Gao and Peihong Xie. An empiricalstudy of online shopping customer satisfaction in China-a holisticperspective[J].International Journal of Retail&Distribution Management,Vol.36No.11:PP919-940.,2008.
[91] CLEMONS E K，GAO Guodong，Hitt L M．When Online Reviews Meet HyperDifferentiation：A Study of the Craft Beer Industry[J]．Journal of ManagementInformation Systerms，Vol.23(2)：PP149—171．,2006.
[92]Hal R.Varian.Intermediate Microeconomics:A Modern Approach.2003,W.W.Norton&Company, Inc. Sixth Edition.
[93] Mudambi，S. M. and Schuff.D. What Makes a Helpful Online Review? A Studyof Customer Reviews on Amazon.com [J].MIS Quarterly. Vol.34:PP185-200.,2010.
[94] Pan，Y. and Zhang，J. Q. Born Unequal: A Study of the Helpfulness ofUser-Generated Product Reviews[J]. Journal of Retailing， Vol.87:PP598~612.,2011.
[95] Stephen Litvin,Ronald Goldsmith,Bing Pan.Electronic word-of-mouth inhospitality and tourism management[J].Tourism Management,(29): PP458-468.,2008.
[96] Chrysanthos Dellarocas.The digitization of word of mouth promise andchallenges of online feedback mechanisms [J].Management Science, Vol.49,No.10:PP1407-1424.,2003.
[97] Wenjing Duan Bin Gu Andrew B. Whionston.The dynamics of onlineword-of-mouth and product sales-An empirical investigation of the movieindustry [J].Journal of Retailing,Vol.84(2):PP233-242.,2008.
[98] Christy M.K.Cheung,Matthew K.O Lee and Neil Rabjohn.The impact ofelectronic word-of-mouth-The adoption of online opinions in online customercommunities[J].Internet Research, Vol.18, No.3:PP229-247.,2008.
[99] Yi-Fen Chen. Herd behavior in purchasing books online[J].Computers inHuman Behavior,(24):PP1977-1992.,2008.
[100] Steven Jones, Darrell Lee,Edward Weis. Herding and feedback tradingby different types of institutions and the effects on stock prices[C],Financial Management Association Meetings,1999.
[101] Jen-Hung Huang. Herding in online product choice [J]. Psychology&Marketing, Vol.23(5): PP413-428.,2006.
[2]娄德成．基于ＮＬＰ技术的中文网络评论观点抽取方法的研究［Ｄ］．上海：上海交通大学，2007.
[3]郝媛媛，叶强，李一军．基于影评数据的在线评论有用性影响因素研究[J]．管理科学学报，2010年第13卷第8期，78-96页．
[4]施国良，石桥峰.基于文本挖掘的不同购物网站商品评论一致性研究[J].现代图书情报技术，2011年第12期，64-68页.
[5]李健.在线商品评论对产品销量影响研究[J].现代情报，2012年第1期，164-167页.
[6]王琦，唐世渭，杨冬青,等.基于DOM的网页主题信息自动提取[J].计算机研究与发展，2004年第41卷第10期，1786-1792页.
[7] CNNIC.2012年中国网民消费行为调查报告.
[8] CNNIC.第31次中国互联网络发展状况统计报告.
[9]埃弗瑞姆.特伯恩（Efrain Turban）、戴维.金（David King）著，电子商务导论（Introduction of Electronic Business），人民大学出版社，2010年第一版。
[10]罗敖生.基于ASP实现网上数据的自动抓取[J].江苏广播电视大学学报，2002年第13卷第6期，59-61页.
[11]朱晓静，方磊坤，李太君.基于P2P网络的信息检索[J].现代电子技术，2007年第4期，120-122页.
[12]顾潇华，郭军城.网页超链抓取及自动分类技术实现[J].河北大学学报（自然科学版），2007年第1期，99-102页.
[13] YU D, SHEIKHOLESLAMI G, ZHANGA. Findout: finding outliers in largedatasets[J]. Knowledge and Information Systems,2002年第4卷第4期，387-412页.
[14]张博，蔡皖东.面向主题的网络蜘蛛技术研究及系统实现[J].微电子学与计算机2009年第5期，52-55页.
[15]袁浩，黄烟波.网页标题分析对主题爬虫的改进[J].计算机技术与发展，2009年第6期，22-28页.
[16]白鹤，汤迪斌，王劲林.分布式多主题网络爬虫系统的研究与实现[J].计算机工程，2009年第35卷第19期，13-19页.
[17]郭会斌.营销口碑的产生路径与创造研究[J].经济与管理.2005年第19卷第l1期，44-46页.
[18]阙克儒.网络匿名性、企业形象与关系品质对网络口碑影响之研究--以线上游戏为例[D].中兴大学,2004.
[19]黄英,朱顺德.二十一世纪的口碑营销及其在中国的发展潜力[J].管理前沿.2003年第6期，33-36页.
[20]郝媛媛.在线评论对消费者感知与购买行为影响的实证研究[D].黑龙江：哈尔滨工业大学，2010.
[21]章晶晶.网络环境下口碑再传播意愿的影响因素研究[D].浙江：浙江大学,2007.
[22]卢向华、冯越.网络口碑的价值——基于在线餐馆点评的实证研究[J].管理世界,2009年第7期，126-132,171页.
[23]周晶晶.在线客户评论对消费者购买决策的影响力研究[D].浙江：浙江大学，2010.
[24]张素华.基于网络外部性与从众效应的锁定策略研究[D].福建：厦门大学，2008.
[25]殷国鹏.消费者认为怎样的在线评论更有用？[J].管理世界，2012年第12期，115-124页。
[26]姜巍，张莉，戴翼，蒋竞和王刚.面向用户需求获取的在线评论有用性分析[J].计算机学报，2013年第1期，121-131页.
[27]杨爽，徐畅.在线产品评论有用性的影响机制[J].求索，2013年第3期，249-251页.
[28]郝媛媛、邹鹏、李一军、叶强.基于电影面板数据的在线评论情感倾向对销售收入影响的实证研究[J].管理评论，2009年第10期，95-103页.
[29]李宏，喻葵，夏景波.负面在线评论对消费者网络购买决策的影响一个实验研究[J].情报杂志，2011年第5期，202-207页.
[30]孟美任，丁晟春.在线中文商品评论可信度研究[J].现代图书情报技术，2013年第9期，60-66页。
[31]李念武，岳蓉.网络口碑可信度及其对购买行为之影响的实证研究[J].图书情报工作，2009第53卷第22期，133-137页.
[32]施国良石桥峰.基于文本挖掘的不同购物网站商品评论一致性研究[J].现代图书情报技术,2011年第12期，64-68页.
[33]潘勇，赵军民.基于顾客满意度的B2C电子商务网站评价[J].现代情报，2008第5期，220-223页.
[34]李思曼，王宇航，李亚平.基于顾客满意的消费者网上购物影响因素分析[J].商业研究，2009第01期，203-206页.
[35]饶曦.网络购物中的消费者购买行为分析[J].现代企业,2010第6期，50-51,57页.
[36]王秀丽田祯祎.网民网络购物行为调查[J].图书情报工作,2011第6期，20-23,95页.
[37]马庆国.管理统计：数据获取、统计原理、SPSS工具应用与研究，科学出版社，2002.08.01.
[38]陈胜可.SPSS统计分析从入门到精通，清华大学出版社，2013.05，第二版.
[39]吴明隆，涂金堂.SPSS与统计应用分析，东北财经大学出版社，2012年9月第一版。
[40]杨维忠，张甜.SPSS统计分析与行业应用案例详解，清华大学出版社，2013年3月第二版。
[41]朱建平，方匡南，章贵军.SPSS统计分析与应用，首都经济贸易大学出版社，2013年2月第一版。
[42] Zhang Z．Weighing stars：Aggregating online product reviews forintelligent e—commerce applications[J]．IEEE Intelligent Systems，Vol.23(5)：PP42—49．,2008.
[43] Tsai F S, Kwee A T. Database Optimization for Novelty Mining of BusinessBlogs [J]. Expert Systems With Applications, Vol.38(9):PP11040-11047.,2011.
[44] Liu Y，Huang X J，An A J，et a1．Modeling and predicting the helpfulnessof online reviews[C].Procedings of the8thIEEE International Conference onData Mining，Washington．DC，USA：IEEE Computer Society：PP443—452．，2008.
[45] Ghose A，Ipeiortis P G．Designing novel review ranking systems：Predictingthe usefulness and impact of reviews[C].Proceedings of the9th ACM Conferenceon Electronic Commerce，Minneapolis， MN，USA：Association for ComputingMachincry：PP303—310．，2007.
[46] Otterbacher J．”Helpfulness”in online communities：A measure of messagequality[C].Proceedings of the27International Conference on Human Factorsin Computing Systems，Boston，MA，USA：Association for Computing Machinery：PP955—964．，2009.
[47] Ye Q，Zhang Z Q，Law R．Sentiment classification of online reviews totravel destinations by supervised machine learning approaches[J]．ExpertSystems with Applications，Vol.36(3)：PP6527—6535.,2009.
[48] Abbasi A，Chen H C，Salem A．Sentiment analysis in multiple languages：Feature selection for opinion classification in web forums[J]． ACMTransactions on Information Systems，Vol.26(3)：PP1—34．,2008.
[49] Abbasi A，Chen H C，Thoms S，et a1．Affect analysis of web forums andblogs using correlation ensembles[J]．IEEE Transactions on Knowledge and DataEngineering，Vol.20(9)：PP1168—1180.,2008.
[50] Kim S M，Pantel P，Chklovski T，et a1．Automatically assessing reviewhelpfulness[C]Proceedings of the Conference Empirical Methods in NatualLanguage Processing，Morristown，NJ，USA：Association for ComputationalLinguistics：PP423—430．，2006.
[51] Chen C C，Tseng Y D．Quality evaluation of product reviews using aninformation quality framework[J]．Decision Support Systems，Vol.50(4)：PP755—768．,2011.
[52] Li N, Wu D D. Using Text Mining and Sentiment Analysis for On Line ForumsHotspot Detection and Forecast [J]. Decision Support Systems,Vol.48(2):PP354-368.,2010.
[53] Chang C W, Lin C T, Wang L Q. Mining the Text Information to Optimizingthe Customer Relationship Management[J]. Expert Systems with Applications,Vol.36(2):PP1433-1443.,2009.
[54] Xu K, Liao S S, Li J, et al. Mining Comparative Opinions from CustomerReviews for Competitive Intelligence[J]. Decision Support Systems,Vol.50(4): PP743-754.,2010.
[55] Gamon M．Sentiment classification on customer feedback data：Noisydata，large feature vectors，and the role of linguistic analysis[C] Proceedingof COLING-04， the20th International Conference on ComputationalLinguistics，Geneva，USA COLING， PP841—847．,2004.
[56] Hu N，Pavlou P A，Zhang J．Overcoming the J-shaped distribution of productreviews [J]．Communications of the ACM，Vol.52(10)：PP144—147．，2009.
[57] Jiang Z H，Benbasat I．Virtual product experience：Effects of visualand functional control of products on perceived diagnosticity and flow inelectronic shopping[J]．Journal of Management Information Systems，Vol.21(3)：PP111—147．,2004。
[58] Jiang Z H，Benbasat I．Investigating the irfluence of the functionalmechanisms of online product presentations[J]．Information Systems Research，Vol.18(4)：PP454—470．,2007.
[59] Pavlou P A，Fygenson M．Understanding and predicting electronic commerceadoption：An extension of the theory of planned behavior[J]．MIS Quarterly，Vol.30(1)：PP115—143．,2006.
[60] Pavlou P A，Liang H G，Xue Y J．Understanding and mitigating uncertaintyin online exchange relationships：A principal—agent perspective[J]．MISQuarterly，Vol.31(1)：PP105—136．,2007.
[61] Kotler P，Keller K．Marketing Management[M]．12ed．，Upper saddle River，NJ：Prentice—Hall，2005．
[62] Kohli R，Devar S，Mahmood M A．Understanding determinants of onlineconsumer satisfaction： A decision process perspective[J]． Journal ofManagement Information Systems，Vol.21(1)：PP115—135．,2004.
[63] Mudambi S M．Schuf D．What makes a helpful online review? A study ofcustomer reviews on Amazon．Com，MIS Quarterly，Vol.34(1)：PP185—200．,2010.
[64] Hevner A R，March S T，Park J，et a1．Design science in information systemsresearch[J]．MIS Quarterly，Vol.28(1)：PP75—105．,2004.
[65] Walls J G，Widmeyer G R，Sawy A E．Building an information system designtheory for vigilant EIS[J]．Information Systems Research，Vol.3(1)：PP36—59．,1992.
[66] March S T，Simith G F．Design and natural—science research on informationtechnology[J]．Decision Support System，Vol.15(4)：PP251—266．,1995.
[67] March S T，Storey V C．Design science in the information systemsdeccipline： An introduction to the special issue on design scienceresearch[J]．MIS Quarterly，32(4)：PP725—730．,2008.
[68] Stigle G J．The econnomics of information[J]．Journal of PoliticalEconomy，Vol.69(3)：PP213—225．,1961.
[69] Chen Y B，Xie J H．Online consumer review：Word-of-mouth as a news elementof marketing communication mix[J]．Management Science，Vol.54(3)：PP477—491．,2008.
[70] Lee T，Bradlow E．Automatic Construction of Conjoint Attributes andLevels from Online Customer Reviews[R]．Florida Decision and InformationSciences Workshop，2007.
[71] Liu J J, Cao Y B, Lin C Y, et al. Low-quality product review detectionin opinion summarization[C].Proceedings of the Joint Conference on EmpiricalMethods in Natural Language Processing and Computational Natural LanguageLearning(EMNLP-CoNLL),Prague: Association Linguistics:PP334-342.,2007.
[72] Emanuel Rosen, Roger E.Scholl.The Anatomy of Buzz: How to CreateWord-of-Mouth Marketing[M]. New York: Random House:PP44-47.,2000.
[73] Blackwell, Roged D., Paul W.Miniard and James F.Engle. ConsumerBehavior[M]. NewYork: Harcount, Inc,2001.9.
[74] Christiansen T., Tax S. S. Measuring word of mouth: the questions ofwho and when?[J]. Journal of Marketing Communications.6(3):185-199.,2000.
[75] Dellaroeas, C. The digitization of word of mouth: Promise and challengesof online feedback mechanisms[J].Management Science. Vol.49(10):PP1407-1424.,2003.
[76] Hennig Thurau, K. P. Gwinner, G. Walsh. D. D. Gremler. Electronicword-of-mouth via consumer-opinion platforms: What motivates consumers toarticulate themselves on the Internet?[J]. Journal of Interactive Marketing.Vol.18(1):PP38-52.2004.
[77] Datta, P. R.，Chowdhury, D. N. and Chakraborty, B. R. Viral marketing:new form of word-of-mouth through Internet [J]. The Business Review,Vol.3(2):PP69-75.,2005.
[78] Katz, E., Lazarsfeld P. F. Personal Influence: The Part Played by Peoplein the Flow of Mass Communication[M]. New York: The Free Press,1964.
[79] Leibenstein, H. Bandwagon, snob, and Veblen. Effeets in the Theory ofConsumers’ Demand [J].The Quarterly Journal of Eeonomies,Vol.64(2):PP183-207.,1950.
[80] Lascu D-N.,Zinkhan G.Consumer Conformity:Review and Applications forMarketing Theory and Practice[J].Jounal of Marketing Theory&Practie.Vol.7(3):PPl-12.,1999.
[81] Banerjee,A.V.A Simple Model of Herd Behavior[J].Quarterly Jounal ofEconomics,Vol.107(3):PP797一817.,1992.
[82] Soo-Min Kim, Patrick Pantel, Tim Chklovski and Marco Pennacchiotti.Automatically Assessing Review Helpfulness [C]. Proceedings of the2006Conference on Empirical Methods in Natural Language Processing,EMNLP:PP423-430.,2006.
[83] Yuanyuan Hao, Qiang Ye, YiJun Li and Zhuo Cheng.How does the Valenceof Online Consumer Reviews Matter in Consumer Decision Making? Differencesbetween Search Goods and Experience Goods[C]. Proceedings of the43rd HawaiiInternational Conference on System Sciences,2010.
[84] Do-Hyung Park and Sara Kim. The effects of consumer knowledge on messageprocessing of electronic word-of-mouth via online consumer reviews[J].Electronic Commerce Research and Applications,(Vol.7): PP399–410.,2008.
[85] Jumin Leea,Park D H, Han I.The effect of negative online consumerreviews on product attitude: An information processing view[J].ElectronicCommerce Research and Applications,(Vol.7):PP341-352.,2008.
[86] Wenjing Duana, Bin Gub, Andrew B. Whinston. The dynamics of onlineword-of-mouth and product sales—An empirical investigation of the movieindustry[J].Journal of Retailing,(Vol.84):PP233-242.,2008.
[87] Garrett P. Sonnier, Leigh McAlister. A Dynamic Model of the Effect ofOnline Communications on Firm Sales. Marketing Science, Vol.30,No.4: PP702-716.,2011.
[88] Judith A. Chevalier and Dina Mayzlin.The Effect of Word of Mouth on Sales:Online Book Reviews[J].Journal of Marketing Research, Vol.43,No.3:PP345-354.,2006.
[89] Qiang Ye, Rob Law, Bin Gu. The impact of online user reviews on hotelroom sales[J]. International Journal of Hospitality Management,Vol.28:PP180-182.,2009.
[90] Xia Liu，Mengqiao He， Fang Gao and Peihong Xie. An empiricalstudy of online shopping customer satisfaction in China-a holisticperspective[J].International Journal of Retail&Distribution Management,Vol.36No.11:PP919-940.,2008.
[91] CLEMONS E K，GAO Guodong，Hitt L M．When Online Reviews Meet HyperDifferentiation：A Study of the Craft Beer Industry[J]．Journal of ManagementInformation Systerms，Vol.23(2)：PP149—171．,2006.
[92]Hal R.Varian.Intermediate Microeconomics:A Modern Approach.2003,W.W.Norton&Company, Inc. Sixth Edition.
[93] Mudambi，S. M. and Schuff.D. What Makes a Helpful Online Review? A Studyof Customer Reviews on Amazon.com [J].MIS Quarterly. Vol.34:PP185-200.,2010.
[94] Pan，Y. and Zhang，J. Q. Born Unequal: A Study of the Helpfulness ofUser-Generated Product Reviews[J]. Journal of Retailing， Vol.87:PP598~612.,2011.
[95] Stephen Litvin,Ronald Goldsmith,Bing Pan.Electronic word-of-mouth inhospitality and tourism management[J].Tourism Management,(29): PP458-468.,2008.
[96] Chrysanthos Dellarocas.The digitization of word of mouth promise andchallenges of online feedback mechanisms [J].Management Science, Vol.49,No.10:PP1407-1424.,2003.
[97] Wenjing Duan Bin Gu Andrew B. Whionston.The dynamics of onlineword-of-mouth and product sales-An empirical investigation of the movieindustry [J].Journal of Retailing,Vol.84(2):PP233-242.,2008.
[98] Christy M.K.Cheung,Matthew K.O Lee and Neil Rabjohn.The impact ofelectronic word-of-mouth-The adoption of online opinions in online customercommunities[J].Internet Research, Vol.18, No.3:PP229-247.,2008.
[99] Yi-Fen Chen. Herd behavior in purchasing books online[J].Computers inHuman Behavior,(24):PP1977-1992.,2008.
[100] Steven Jones, Darrell Lee,Edward Weis. Herding and feedback tradingby different types of institutions and the effects on stock prices[C],Financial Management Association Meetings,1999.
[101] Jen-Hung Huang. Herding in online product choice [J]. Psychology&Marketing, Vol.23(5): PP413-428.,2006.