在线商品评论有用性影响因素研究

网络商务发展中产生了大量无效甚至恶意的在线评论,给消费者阅读和参考带来一定负面影响。针对上述问题,提出了一种基于多元线性回归算法的在线评论有用性预测方法。该方法综合考虑了评论文本属性、评论者属性和店铺属性这三个影响因素,并构建一个预测在线评论有用性模型——RRS-L模型。在实际数据集上的实验表明：该模型具有较高的查准率与召回率,能有效过滤无用评论。     

基于社交媒体的在线评论感知有用性预测模型

社交媒体的广泛应用使得人们获取、分享信息更加便捷,在线评论是内容共享型社交媒体的典型代表,能帮助消费者快速制定购买决策。依据信息经济学理论和信息采纳模型,研究影响商品在线评论感知有用性的主要因素,构建了在线商品评论感知有用性预测模型,并以亚马逊网站上商品的实际评论数据进行了实证分析。结果表明,评论深度、评论者可信度、评论情感倾向和评论及时性与感知有用性为正相关关系,并根据研究结果对电商企业管理提出相关建议。     

基于评论有用性投票的低频关键词提取方法研究

在互联网环境下,许多消费者在购买商品之前都会参考网上的评论信息以及星级评价,比如五星好评.但是这些评论大多都是一些个人主观的评价,带有个人感情色彩,有的时候是片面的.如何从大量评论中找到有价值的信息成为研究的重点和难点.针对这一问题,文中提出有关在线评论有用性投票的分析方法.在实验中,利用论文的方法来提取评论集只出现一...     

面向用户需求获取的在线评论有用性分析

在线评论已成为互联网环境下用户需求获取的重要数据资源.然而,评论质量的良莠不齐严重干扰了需求挖掘的准确性和可信性.如何发现能够准确描述用户需求的有用评论是提高需求获取技术有效性的前提保障.针对这一问题,文中提出一种基于复杂网络的评论有用性分析方法,利用评论间的语义关联,从宏观的角度分析评论对于用户需求识别的有用程度,进而发现能够准确描述用户需求的评论.作者将评论看作一种内容互连的网络拓扑的形态,利用评论网络节点的重要性来度量评论的有用性,并通过拓扑势理论将用户的主观评价与网络拓扑结构的客观影响有机融合对评论网络节点重要性进行分析.实验结果表明,该方法所确定的高有用性评论能够保证用户需求获取具有较高的准确率和覆盖率.     

面向产品设计改进的在线评论挖掘

以竞争市场环境中的产品在线评论数据为研究对象,基于支持产品设计改进的视角,采用数据挖掘的方法与工具,开展面向产品设计改进的在线评论大数据分析研究。重点开展在线评论数据挖掘过程模型中的有用性建模和特征评价值情感分析。以某智能手机产品的在线评论数据为对象进行了实验,得到该产品各个属性的评价值,与更新换代后的产品属性进行比较,验证了此方法的有效性。     

企业在线反馈评论对潜在客户感知可信度及沟通质量影响的实证研究

以新兴的电子商务购物模式为问题背景,从浏览评论的潜在客户的视角,在对现有研究梳理和总结的基础上,结合消费者在线评论的特点,提出了影响潜在顾客对企业反馈评论感知可信度的模型。整个过程以网站提供的评论为样本,通过实证研究的方式,对企业反馈在线评论对潜在消费者带来的感知可信度以及沟通质量进行了研究。     

基于书写行为与语义特征的评论有用性评估

针对电子商务网站充斥着大量有用性较低的评论,提出一种基于用户书写行为与语义特征的中文评论有用性评估方法。方法通过在Web客户端实时监听评论文本框值的变化,识别出句尾插入、非句尾插入、句尾删除、非句尾删除等书写行为,在服务器端根据书写行为、评论的语义特征建立的线性评估模型计算用户评论的有用性。实验结果表明该方法能够较为准确地识别有用性较高的评论。     

中文在线评论中产品特征抽取研究

在线评论中特征抽取是产品意见挖掘的基础,直接影响到最终挖掘结果的准确性。针对现有特征抽取方法的准确率和召回率偏低问题,该文通过设计词性序列模板产生候选特征集,利用PMI-IR方法进行筛选,最终获得产品特征集。实验结果表明,该方法取得较好效果。     

基于语义规则与RNN模型的在线评论情感分类研究

为提高互联网中在线评论文本的情感倾向分类准确率,方便消费者和商家准确高效地获取信息,该文提出一种将语义规则方法与深度学习方法相结合的在线评论文本情感分类模型,对基于情感词典的语义规则信息进行扩展,嵌入到常用特征模板中组合成更有效的混合特征模板;采用Fisher判别准则方法对混合特征模板进行降维以消除特征间的信息冗余;深度学习模型采用基于LSTM改进的RNN模型,将网络爬取的数据输入到模型进行训练和测试。结果表明,语义规则抽取出的特征包含更多、更准确的情感信息,使得混合特征模板可以更加全面地考虑文本的情感特征粒度;Fisher准则可有效识别出高判别性的低维文本特征,进一步提高改进RNN模型对评论文本的分类性能。     

Helpfulness of user-generated reviews as a function of review sentiment,product type and information quality

Helpfulness of user-generated reviews has not been studied adequately in terms of the interplay between review sentiment (favorable, unfavorable and mixed) and product type (search and experience). Moreover, the ways in which information quality relates to review helpfulness remain largely unknown. Hence, this paper seeks to answer the following two research questions: (1) How does the helpfulness of user-generated reviews vary as a function of review sentiment and product type? (2) How does information quality relate to the helpfulness of user-generated reviews across review sentiment and product type? Data included 2190 reviews drawn from Amazon for three search products—digital cameras, cell phones, and laser printers—as well as three experience products—books, skin care, and music albums. Review sentiment was ascertained based on star ratings. Investigation of the research questions relied on the statistical procedures of analysis of variance, and multiple regression. Review helpfulness was found to vary across review sentiment independent of product type. Besides, the relationship between information quality and review helpfulness was found to vary as a function of review sentiment as well as product type. The paper concludes with a number of implications for research and practice.     

An examination of the celebrity endorsements and online customer reviews influence female consumers’ shopping behavior

The goal of this study is to compare the influence of celebrity endorsements to online customer reviews on female shopping behavior. Based on AIDMA and AISAS models, we design an experiment to investigate consumer responses to search good and experience good respectively. The results revealed that search good (shoes) endorsed by a celebrity in an advertisement evoked significantly more attention, desire, and action from the consumer than did an online customer review. We also found that online customer reviews emerged higher than the celebrity endorsement on the scale of participants’ memory, search and share attitudes toward the experience good (toner). Implications for marketers as well as suggestions for future research are discussed.     

基于LDA主题模型和直觉模糊TOPSIS的农产品在线评论情感分析

本文提出了基于LDA主题模型和直觉模糊TOPSIS的农产品在线评论情感分析方法。该方法使用情感词典对在线评论进行情感倾向分析,并计算农产品的积极情感值;运用LDA主题模型计算各个属性的权重,结合直觉模糊TOPSIS方法计算农产品的综合评价值;采用SPSS统计分析软件进行有效性检验。结果表明,综合评价值与月销售量、积极情感值呈显著的正相关性,说明该方法具有合理性,为挖掘农产品在线评论中的情感信息提供一种新的思路。     

客户评论中用户体验信息自动提取研究

客户评论在人们的日常生活中越来越重要,人们希望从客户评论中获取商品的用户体验信息.客户评论数量的急剧增长使得用户快速、精准地获取有用的信息变得较为困难.为此,提出一种能够自动提取用户体验信息的方法.该方法通过语义片段过滤评论中的冗余信息,提取产品特征词及特征描述词,将其结合组成用户体验信息,自动获取信息能够迅速、准确地从客户评论中提取信息.实验结果证明了该方法的有效性,并且能够保证较高的准确率与查全率.     

电子商务客户流失的DBN预测模型研究

在电子商务迅速发展,企业快速抢占市场的背景下,客户成为企业竞争的核心因素。现有相关研究多致力于采用全数据输入模式解析客户流失现象,不同类型客户造成的差异性还有待进一步探讨。鉴于传统RFM模型不能精确解释电子商务客户流失原因,该研究将客户分为活跃与非活跃两个集群,提出一种优化的RFM理论模型与深度信念网络实证模型对电子商务客户流失进行预测。结果表明,不同类型客户流失因素的影响强度不同。对活跃用户而言,客户购买总金额是影响客户流失的主要因素;对非活跃用户而言,客户进入店铺的时间越长越可能留住客户。通过剖析非活跃用户不流失和活跃用户流失的原因,可帮助企业制定有效的客户管理策略,以最大程度地吸引潜在客户及保留现有客户,获取最多的市场利益。     

Online customer reviews and consumer evaluation: The role of review font

Inspired by the literature on processing fluency and the practical question of how to choose fonts for website design, we investigated the impact of customer reviews on consumer evaluation under an easy-to-read (vs. difficult-to-read) review font. We found that the feeling of ease in reading led consumers to judge the reviewers as more credible, thus increasing the impact of the reviews. Moreover, the effect of font diminished when consumers elaborated information more thoroughly (i.e., when high in need for cognition, or in an accountable situation) and thus did not use simple heuristics (reading ease) to make judgment.     

中文网络评论中提取产品特征的研究

大量的网络评论已经成为挖掘用户意见、改进产品质量的重要信息来源,而特征抽取作为后续分析的基础,直接影响到最终意见挖掘结果的准确性. 本文提出了一种PMI-Bootstrapping算法,并结合了语言规则实现中文网络评论的产品特征抽取. 首先利用语言规则产生候选特征集,计算每个候选特征与初始给定种子集的加权平均互信息,将满足阈值的候选特征添加到种子集中,如此循环迭代,直到种子集合收敛,输出排队后的种子集合作为抽取结果. 实验证明,该算法取得良好的准确率和召回率.     

以客户需求为导向的定制终端潜在客户挖掘模型研究

本文设计了以客户需求为导向的定制终端潜在客户挖掘模型,不仅要有效地挖掘出有换机需求的潜在客户,同时根据各类用户的特征,为其匹配相应价位的终端,并通过市场部门在第一时间向用户开展主动营销,提升终端销量及用户消费能力。     

Perceived derived attributes of online customer reviews

The influence of online customer reviews (OCRs) on customers' purchase intention has recently gained considerable attention, in both academic and business communities. Technology allows customers to freely and easily post their comments and opinions online about any product or service; this type of customer review can have a significant effect on customers' purchase decisions. Previous studies, however, have mainly focused on the influence of the virtual attributes of OCRs such as volume and valence on consumers' intentions, while limited attention has been paid to understanding the effects of the derived attributes. This study, thus, aims to understand the impact of the perceived derived attributes of OCRs on customer trust and intention. This study develops a – Perceived Derived Attributes (PDA) - model, based on the inclusion of perceived control from the Theory of Planned Behaviour (TPB) with the Technology Acceptance Model (TAM), in order to investigate the effects of OCRs on customers’ purchasing intention. A total of 489 responses to a survey were collected from users of amazon.com. The findings from this study suggest that customer trust in an e-vendor and their intention to shop online are significantly affected by perceived usefulness, perceived ease of use and perceived enjoyment of OCRs. Furthermore, the sense of control derived from OCRs significantly affects customer intention and significantly affects customer trust in e-vendors, particularly for customers who frequently check OCRs before making a purchase. Clearly, those attributes of OCRs are linked to the development of the shopping environment, which consequently can affect sales.