Herd behavior in purchasing books online

Previous studies on informational cascades have stressed the importance of informational social influences in decision-making. When people use the product evaluations of others to indicate product quality on the Internet, online herd behavior occurs. This work presents four studies examining herd behavior of online book purchasing. The first two studies addressed how two cues frequently found on the Internet, i.e., star ratings and sales volume, influence consumer online product choices. The last two studies investigated the relative effectiveness of different recommendation sources. The experimental results demonstrated that subjects use the product evaluations and choices of others as cues in making purchasing book decisions on the Internet bookstore. Additionally, recommendations of other consumers exerted a greater influence on subject choices than recommendations of an expert. Finally, recommendations from recommender system influenced online consumer choices more than those from website owners. The results and implications of this research are discussed.     

A classification-based review recommender

Many online stores encourage their users to submit product or service reviews in order to guide future purchasing decisions. These reviews are often listed alongside product recommendations but, to date, limited attention has been paid as to how best to present these reviews to the end-user. In this paper, we describe a supervised classification approach that is designed to identify and recommend the most helpful product reviews. Using the TripAdvisor service as a case study, we compare the performance of several classification techniques using a range of features derived from hotel reviews. We then describe how these classifiers can be used as the basis for a practical recommender that automatically suggests the most-helpful contrasting reviews to end-users. We present an empirical evaluation which shows that our approach achieves a statistically significant improvement over alternative review ranking schemes.     

Effects of consumer characteristics on their acceptance of online shopping: Comparisons among different product types

Previous electronic commerce (EC) studies have found that consumer characteristics are important when considering issues related to the acceptance of online shopping. However, most studies have focused on a single product or similar products. The effects of different product types have been relatively neglected. Previous studies have limited the generalizability of their results to a few products at best. To overcome this limitation, the purpose of this study was to explore the effects of different product types. The Internet product and service classification grid proposed by Peterson, Balasubramanian and Bronnenberg (Peterson, R. A., Balasubramanian, S., & Bronnenberg, B. J. (1997). Exploring the implications of the Internet for consumer marketing. Journal of Academy of Marketing Science, 25(4), 329–346) was employed to examine the effects of consumer characteristic differences on online shopping acceptance in the context of different products and services. A survey-based approach was employed to investigate the research questions. Regression analysis demonstrated that the determinants of online shopping acceptance differ among product or service types. Additionally, personal innovativeness of information technology (PIIT), perceived Web security, personal privacy concerns, and product involvement can influence consumer acceptance of online shopping, but their influence varies according to product types.     

Perceptions of Customer Service,Information Privacy,and Product Quality From Semiotic Design Features in an Online Web Store

The rise of the World Wide Web for electronic commerce has led to a proliferation of companies selling products online. The global nature of the Internet allows customers to browse the products of companies with which they are wholly unfamiliar. However, concerns about customer service, information privacy, and product quality discourage purchasing from unknown companies. In this article, the effects of semiotic Web design features on expectations of these performance criteria in a purchase situation are investigated. Specifically, the presence and prominence of links to customer service and a site privacy policy, and the existence of product ratings and customer testimonials, were tested to measure their effects on customer perceptions and expectations. Results indicate that some design features have a strong semiotic effect on customer expectations. Prominent links to customer service and a site privacy policy significantly increased expectations of customer service and privacy protection. The presence of product ratings increased perceptions of product quality. All 3 design features led to increased likelihood of purchase. Furthermore, participants were not aware of these effects and reported not considering product ratings in their decisions. Implications of these results on Web site design and consumer behavior are discussed.     

Likelihood to abort an online transaction: influences from cognitive evaluations,attitudes, and behavioral variables

This study identifies evaluative, attitudinal, and behavioral factors that enhance or reduce the likelihood of consumers aborting intended online transactions (transaction abort likelihood). Path analyses show that risk perceptions associated with e-shopping have direct influence on the transaction abort likelihood, whereas benefit perceptions do not. In addition, consumers who have favorable attitudes toward e-shopping, purchasing experiences from the Internet, and high purchasing frequencies from catalogs are less likely to abort intended transactions. The results also show that attitude toward e-shopping mediate relationships between the transaction abort likelihood and other predictors (i.e., effort saving, product offering, control in the information search, and time spent on the Internet per visit).     

Assessing the impact of recommender agents on on-line consumer unplanned purchase behavior

Recommendation agents (RAs) have been used by many Internet businesses such as Amazon and Netflix. However, few authors have studied how consumer behavior is affected by those that make suggestions to online consumers based on their recent shopping behavior. Fewer still have examined the role that RAs play in influencing impulse purchasing decisions online. Our study developed a theoretical model to illustrate the impact of RAs on online consumer behavior. The model was tested through an online shopping simulation which used a collaborative filtering based product RA. Particular attention was paid to the effects of an RA on consumer behavior; we found that it increased promotion and product search effectiveness, user satisfaction with the website, and unplanned purchases. Results showed that our model provided insights into the impact of an RA on online consumer behavior and thus provided suggestions for implementing effective systems.     

Marketing on the Internet — who can benefit from an online marketing approach?

The research builds upon the literature in electronic commerce and past research in marketing with the objective of understanding factors that impact a product's adaptability to online marketing. A review of marketing channel choice literature reveals a set of factors and channel choice functions that are considered important in making channel decisions. Using this as a basis, four major channel functions, namely, product customization, availability, logistics, and transaction complexity are considered relevant in understanding the implications for Internet marketing. By building upon previous research in the area of channel selection, we provide a means of classifying Internet marketing initiatives based on product characteristics. The classification scheme based on product characteristics can help analyze the significance of each factor on the success of a firm's online marketing approach. Further, the classification scheme is used to discuss decision support implications.     

Online information search and decision making: Effects of web search stance

A naturalistic online information search exposes individuals to multiple sites and conflicting perspectives. In this study, we evaluated how the holistic stance of a web search toward a product influences purchasing decisions. We recruited 109 participants who completed an initial product choice task regarding bottled water, a brief Internet search, and then a second post-search product choice task. Internet searches were analyzed to identify query terms, site visits, and stance. Results show that query terms influenced the types of sites obtained in a search, which in turn shaped the overall search stance. Participants were more likely to buy bottled water when they visited websites that emphasized environmental, economic, or health benefits for bottled water (i.e., positive stance). Participants who were asked to focus on environmental issues were less likely to buy bottled water unless packaged in recycled plastic.     

The impact of perceived ease of use on Internet service adoption: The moderating effects of temporal distance and perceived risk

Perceived ease of use is found to affect consumer’s intention toward using an Internet-based service. However, to protect online transaction security, more security verification mechanisms are established which in turn increase the complexity and difficulty of using online services. This study proposed that the importance of perceived ease of use is depending on short- vs. long-term transaction expectation, product type, and whether security concern information is presented. In certain situations buyers or sellers of an Internet service may tolerate the inconvenience of using the Internet-based service. A 2 (verification requirement) × 2 (network externality) × 2 (short vs. long term) between-subject design was conducted on sellers of an auction site and a 2 (verification requirement) × 2 (product type) × 2 (with vs. without security concern information) between-subject design was conducted on buyers of an auction site. The results of two studies suggest that perceived ease of use increases the intention toward using online service when sellers expect that the Internet service usage is only for a short-term transaction or when buyers have no access of the security concern information on the website. In contrast, sellers prefer using an online service which requires a relatively high verification requirement when the purpose of using Internet service is for long-term transaction or when buyers have access of security concern information. The results also showed that perceived network externality positively affect sellers’ intention toward using an auction website.     

Price competition in e-tailing under service and recognition differentiation

The Internet has significantly increased the bargaining power of consumers. Many online shopping search engines allow consumers to find most retailers that sell a specific product, compare product prices, and review detailed store ratings. With competition just a click away, online retailers have little control over where consumers would shop. Offering the lowest price alone does not always guarantee that consumers will come and buy at your site. Other non-price attributes, such as service quality and a merchant’s brand recognition, also play important roles in helping online retailers to build competitive advantages. In this paper, we present a model of price competition that assumes e-tailers can mainly differentiate themselves by providing different levels of service and by establishing a different online recognition. Closed-form equilibrium solutions are obtained for the different scenarios that may arise in this model. Based on such solutions, we give managerial insights on how e-tailers should position themselves when parameters such as service cost, service levels, and recognition are varied.     

基于深度学习的女装图片分类探索

互联网商品图像的属性分类是人工智能领域的重要研究课题之一,针对商品图像属性分布不 平衡以及不同属性间存在相关性等问题,该文以女装图像为分类目标,提出了一种基于卷积神经网络的商品图像分类方法。首先,从电商网站获取大量商品图像,并进行人工标注;然后,基于卷积神经 网络框架,采用了一种有效的采样策略,通过增加新的损失函数,实现了基于多任务学习方法的商品图像属性准确分类;最后,通过对不同策略下分类结果的对比分析,验证了该方法的有效性。结果显 示,所提出方法具有较高的分类精度。     

Obelix searches Internet using customer data

One major problem with purchasing through the Web is locating reliable suppliers that offer the exact product or service you need. In the usual approach, you access an indexing based search engine, specify keywords for the purchase, and initiate the search. The outcome is typically a list ranked according to keyword matches; useful, but not always helpful. Keyword matches provide only one ingredient to finding the right Web sites. The ranking should also consider the satisfaction of previous customers purchasing from those sites, customer profiles, and customer behavior. The Obelix search engine uses reconfigurable technology to apply customer satisfaction data obtained from the Internet service provider infrastructure to refine its search criteria. The Obelix system collects data about customer activities, calculates a customer satisfaction index, and updates the search engines with its findings     

一种基于UDDI构建软组件库的方法*

为了满足软组件重用者在互联网环境下共享软组件资源的需要,提出了一种基于UDDI注册机制使用Web 服务技术构建软组件库的方法。利用UDDI 2.0支持外部分类法的特性,将改进后的刻面分类法以tModel的形式注册到UDDI注册中心,并给出与该分类法相对应的分类验证服务的简单描述。此外,扩充了UDDI的查询功能,将实现查询匹配的服务集成到UDDI中,提供对多种服务描述语言的支持。     

Does source matter? Examining source effects in online product reviews

Drawing on the literature about online source classification, source credibility, and attribution theory, this study examines how the source of a product review influences people’s product judgments. Results from a between-subjects experiment suggest that the perceived source of a message (the visible source) impacts how people evaluate actual reviewer (the original source) and product. Reviews made by regular Internet users (visible sources) lead to greater trust in the actual reviewer (the original source), compared to product reviews from product makers. Results further indicate that visible sources play a crucial role in helping people judge the credibility of online reviews. Particularly, the identity of a visible source is used to consider the intention of original source of the message, which in turn determines message persuasiveness. The authors conclude that evaluating the intentions of online reviewers is a critical antecedent to forming opinions about online reviews and products.     

The moderating effects of psychological reactance and product involvement on online shopping recommendation mechanisms based on a causal map

The use of the Internet in the daily activities of individuals and firms has become entrenched, and online shopping has become commonplace. However, debates about how online shopping recommendation mechanisms (OREMs) should be designed have not been completely resolved. The challenge with traditional online shopping recommendation mechanisms (TR-OREMs) is that they focus too much on quantitative factors. Thus, they ignore causal interrelationships with qualitative factors that are believed to significantly impact quantitative factors. Considering only quantitative factors and ignoring qualitative ones likely distorts the final recommendation results. Another problem with TR-OREMs is that they ignore the perceived psychological reactance of consumers against the recommended products. Such consumer reactance may be reduced when the causal interrelationships among all the quantitative and qualitative factors are analyzed and incorporated properly into the OREM. To overcome these problems, we propose a causal map – online shopping recommendation mechanisms (CM-OREMs) based on a causal map. We analyzed possible causal relationships among quantitative and qualitative factors and incorporated them in the recommendation process to reduce consumer reactance against the recommendation results. Furthermore, an elaboration likelihood model (ELM) was used to build hypotheses about how the online shopping behavior of consumers is affected by OREMs based on the proposed causal map. Specifically, the performance of the proposed OREM was empirically analyzed by gathering experiment data from qualified respondents who were asked to refer to the proposed OREM before making purchasing decisions via mobile phones. Statistical results showed that the proposed OREMs could enhance consumer decision satisfaction, decision confidence, and attitude toward the recommended products. It could also positively affect consumer purchasing intentions. The OREM had a greater effect on the high-reactance group of participants than on the low-reactance group as well as on a high-involvement product versus a low-involvement product.     

基于情感词抽取与LDA特征表示的情感分析方法

情感分析作为文本挖掘的一个新型领域,可用于分类、归纳用户发布的产品评论,从而有助于商家改善服务,提高产品质量;同时为其他消费者提供购买决策。本文提出一种基于情感词抽取与LDA特征表示的情感分析方法,对产品评论进行褒贬二元分类。在情感词抽取中,采用人工构造的情感词典对预处理之后的文本抽取情感词;用LDA模型建立文档的主题分布,以评论-主题分布作为特征,用SVM分类器进行分类。实验结果表明,本文方法在评论褒贬分类方面有着良好的效果。     

Segmenting customers in online stores based on factors that affect the customer’s intention to purchase

This study has proposed an approach that enables online stores to offer customized marketing by segmenting their customers based on customers’ psychographic data. Online stores can concentrate on more profitable activities by identifying customers’ value as they segment their customers into a few groups of customers with similar intentions to purchase. To segment online customers, based on previous research that explains the behavior of online customers regarding purchasing, the approach has employed the factors that affect the customers’ intention to purchase on the Web. We integrated the clustering results of SOM (self-organized map) and the k-means algorithm into a single model. Online stores can develop promotional marketing and offer personalized service for e-customers, who are more valuable and more promising, according to the market segments presented by our approach.     

基于HttpClient的代购同步技术研究与实现

网络代购作为电子商务的一种形式,已经发展的十分成熟.人们不再仅限于参与本国的网络购物,而是越来越多地参与各国知名电子商务网站的购买活动.由于种种原因,导致跨国度网上购物难以实现,于是出现了代购网站,提供国外代购服务.提出的代购同步技术,是一种新型的代购网站解决模型.首先,使用HttpClient抓取国外电子商务网站页面的数据用于展示,保证信息的实时性、减少了系统数据库的开销.再使用HttpClient将用户的每一次购买请求,同步到国外的电子商务网站当中,直接完成真正的购买行为.该模型具有更好的自动性、通用性和稳定性.