消费者在线评论有用性影响因素模型研究

消费者在线评论的价值已经得到消费者和在线零售商的公认,对评论有用性的研究已经成为新的研究热点。从减少消费者决策风险出发,在感知诊断性概念基础上定义了评论有用性概念,构建了一个评论有用性影响因素模型。从传播说服理论的维度考察,评论等级、评论长度、好评率和使用互联网经验是影响评论有用性的重要因素。商品类型对评论有用性具有调节作用。     

挖掘中文网络客户评论的产品特征及情感倾向*

为探索中文客户评论中的产品特征及相关情感倾向的挖掘,以帮助生产商和服务商改进产品、改善服务,提高竞争力,提出采用基于Apriori算法的非监督型产品特征挖掘算法,结合监督型情感分析技术,实现对于评论中产品特征及其情感倾向的综合信息挖掘;并根据用户的关注权重将产品特征和情感倾向进行排列。采用几种从互联网下载的真实产品评论语料,对该方法进行了数据实验,实验结果初步验证了该方法的有效性。     

基于情感极性与SMOTE过采样的虚假评论识别方法*

为了有效识别商品虚假评论,提出一种基于情感极性与SMOTE过采样的虚假评论识别方法。首先,根据在线虚假评论的特点,构建一个多维虚假评论特征模型。其次,在情感极性算法中增加了情感极性均值和情感极性标准差等统计指标来全面刻画虚假评论。最后,针对虚假评论中的类不平衡问题,使用SMOTE算法优化随机森林分类模型,从而提高虚假评论识别效果。基于大众点评网的真实评论数据进行了多组实验,实验结果表明该方法在正负样本不平衡的虚假评论数据集中具有更高的准确率、召回率及F值。综合考虑情感极性和正负样本不平衡等因素可帮助电商平台有效过滤虚假评论,为消费者提供更加真实可靠的评论数据。     

Search product and experience product online reviews: An eye-tracking study on consumers' review search behavior

This study uses eye-tracking method to investigate consumers' online review search behavior by suggesting that it needs to consider the type of product reviewed. A review-product congruity proposition was testified through a self-report survey and an eye-tracking experiment. The proposition states that consumers of search products expect to seek attribute based reviews, while consumers shopping for experience products tend to seek experience based reviews. Two experiments were conducted in the human factors & ergonomics laboratory of Beihang University, China and all subjects are college students. The results of our first empirical experiment support our hypotheses by showing consumers' more active and positive responses to attribute based reviews when shopping for search products and to experience based reviews when purchasing experience products. The second experiment was conducted with eye tracking method to gain further insights. We found that consumers of search products are attracted and engaged more deeply by attribute based reviews. However, when they browse experience products, the difference of their fixations on experience based reviews and attribute based reviews is not significant, and thus the proposition is partially supported. This study extends our current understanding of consumers' online review search behavior by subsuming product type, which is necessary and helpful, and provides references on the classification and presentation of reviews to facilitate consumers' product judgement and decision making. Moreover, comparison of traditional empirical method and eye-tracking method can help deepen our understanding of complex consumer online shopping behavior.     

Sources and impacts of social influence from online anonymous user reviews

Consumers increasingly rely on online reviews to make purchase decisions. However, the process through which consumers are influenced by online reviews is not well understood. To fill the gap, we apply the social influence theory to theoretically explain and analyze this opinion change process. Specifically, we identify antecedents and consequences of two types of social influence from online user reviews: informational and value-expressive influence. From a survey conducted in a controlled laboratory environment, we found that perceived review quality positively impacts informational influence, while perceived review quality, consistency, and social presence jointly impact value-expressive influence. Interestingly, informational influence impacts both perceived decision quality and perceived usefulness of the website, while value-expressive influence only impacts perceived usefulness of the website. Surprisingly, consumer characteristics, including prior product expertise and self-monitoring, do not have significant effects on the formation of social influence online.     

Trusting expert- versus user-generated ratings online: The role of information volume,valence, and consumer characteristics

The warranting principle, signaling theory, and theories of informational social influence suggest conditions when either user-generated information, or information originating from traditional experts, might be privileged online. A random sample of 1207 U.S.-based adults with Internet access completed an experiment that manipulated the source, volume, and valence of online movie ratings in order to test predictions derived from these perspectives. Results indicated that ratings volume is positively associated with trust of, reliance on, and confidence in user-generated content, as well as the congruence between one’s own and others’ opinions; that ratings source and volume interact to impact credibility perceptions, reliance on user-generated information, and opinion congruence, such that people tend to favor experts when there is low information volume, but favor user-generated information under conditions of high information volume; and that people’s opinions and behavioral intentions converge with the online ratings information to which they are exposed. In addition, these effects apply more strongly to people more conversant with user-generated content. Results indicate important theoretical extensions by demonstrating that social information online may be filtered through signals indicating its veracity, which may not apply equally to all social media users.     

Impact of online word-of-mouth on sales: the moderating role of product review quality

Facing with thousands of online product reviews, consumers usually pay close attention to those valuable ones which provide more specific and credible evaluations on products. Whether a close association exists between product review quality and sales is thus examined in this paper. By employing text mining techniques on multiple review features, a review is measured as one of the following two levels: high-quality or low-quality. In doing so, aggregate quality level of product’s whole reviews is also identified. Then, a two-level econometrical analysis is conducted on the real datasets from Amazon.cn. The results reveal that aggregate quality level of positive reviews and negative reviews interactively influence sales. In the situation the aggregate quality level of positive reviews is high meanwhile that of negative reviews’ is low, product sale is the highest, while in the opposite situation product sale is the lowest. The results also reveal that consumers understand product’s value from weighting positive and negative reviews of high-quality level, which then positively relates to product sales and exerts a dynamic effect on sales by the moderating role of product selling stage and popularity. The paper innovatively integrates the quantitative and qualitative characteristics of reviews to estimate their economic effect.     

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.     

On the use of information fusion techniques to improve information quality: Taxonomy,opportunities and challenges

The information fusion field has recently been attracting a lot of interest within the scientific community, as it provides, through the combination of different sources of heterogeneous information, a fuller and/or more precise understanding of the real world than can be gained considering the above sources separately. One of the fundamental aims of computer systems, and especially decision support systems, is to assure that the quality of the information they process is high. There are many different approaches for this purpose, including information fusion. Information fusion is currently one of the most promising methods. It is particularly useful under circumstances where quality might be compromised, for example, either intrinsically due to imperfect information (vagueness, uncertainty, …) or because of limited resources (energy, time, …). In response to this goal, a wide range of research has been undertaken over recent years. To date, the literature reviews in this field have focused on problem-specific issues and have been circumscribed to certain system types. Therefore, there is no holistic and systematic knowledge of the state of the art to help establish the steps to be taken in the future. In particular, aspects like what impact different information fusion methods have on information quality, how information quality is characterised, measured and evaluated in different application domains depending on the problem data type or whether fusion is designed as a flexible process capable of adapting to changing system circumstances and their intrinsically limited resources have not been addressed. This paper aims precisely to review the literature on research into the use of information fusion techniques specifically to improve information quality, analysing the above issues in order to identify a series of challenges and research directions, which are presented in this paper.     

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.     

eWOM source credibility,perceived risk and food product customer's information adoption

This study examined the relations between source credibility of eWOM (electronic word of mouth), perceived risk and food products customer's information adoption mediated by argument quality and information usefulness. eWOM has been commonly used to refer the customers during decision-making process for food commodities. Based on this study, we used Elaboration Likelihood Model of information adoption presented by Sussman and Siegal (2003) to check the willingness to buy. Non-probability purposive samples of 300 active participants were taken through questionnaire from several regions of the Republic of China and analyzed the data through structural equation modeling (SEM) accordingly. We discussed that whether eWOM source credibility and perceived risk would impact the degree of information adoption through argument quality and information usefulness. It reveals that eWOM has positively influenced on perceived risk by source credibility to the extent of information adoption and, for this, customers use eWOM for the reduction of the potential hazards when decision making. Companies can make their marketing strategies according to their target towards loyal clients' needs through online food- product forums review sites.     

The effect of content depth and deviation on online review helpfulness: Evidence from double-hurdle model

How does the content of a product review shape its perceived value? We propose two information theory-based constructs derived from probabilistic topic models and show their relationship with review helpfulness. The first construct, content depth, quantifies the breadth-depth tradeoff of a review and has an informational influence on readers’ voting behavior. The second construct, content deviation, indicates the deviance of the review content in comparison with others and exerts a normative influence on readers’ voting behavior. Noting the possibility that a review can get voted but has zero helpfulness score, we use a double-hurdle model to simultaneously estimate the probability of a review being voted and its helpfulness. The analyses on three product categories show that reviews with more depth and less content deviation are rated more helpful. Further, the relationships are moderated by a number of factors, including the deviation of numerical rating, recency of the review, and the reputation of the reviewer. The research contributes to the literature by showing how the content of a review and the interaction of content and numerical ratings jointly create value for consumers.     

Assessing information quality of e-learning systems: a web mining approach

E-learning systems provide a promising solution as an information exchanging channel. Improved technologies could mean faster and easier access to information but do not necessarily ensure the quality of this information; for this reason it is essential to develop valid and reliable methods of quality measurement and carry out careful information quality evaluations. This paper proposes an assessment model for information quality in e-learning systems based on the quality framework we proposed previously: the proposed framework consists of 14 quality dimensions grouped in three quality factors: intrinsic, contextual representation and accessibility. We use the relative importance as a parameter in a linear equation for the measurement scheme. Formerly, we implemented a goal-question-metrics approach to develop a set of quality metrics for the identified quality attributes within the proposed framework. In this paper, the proposed metrics were computed to produce a numerical rating indicating the overall information quality published in a particular e-learning system. The data collection and evaluation processes were automated using a web data extraction technique and results on a case study are discussed. This assessment model could be useful to e-learning systems designers, providers and users as it provides a comprehensive indication of the quality of information in such systems.     

Collaborative engineering decision-making for building information channels and improving Web visibility of product manufacturers

Product manufacturers have spent the last years improving productivity and process efficiency in order to face increasingly competitive markets. Today, the visibility of technological innovations has become essential to achieve the targeted market. It is now very difficult for a product manufacturer to reach customers without owning a website that is visible on search engine results pages. The goal of this paper is to build information channels between a company and its customers through improving both a company’s content of information on the Web and its website rank on the Internet through search engine results pages. Company information and knowledge are distributed through multiple stakeholders. The problem of building information channels between a company and customers is solved through a collaborative and distributed approach, on the one hand, and is supported by decision-making tools, on the other hand. The paper proposes an engineering model for building information channels and improving the visibility of the company on the Web. Agents are used for the implementation of the approach. The proposed model and its implementation handle the requirements, constraints, functions and solutions for improving Web visibility. The prototype tool, called CAWIS (Computer Aided Web Information Sharing), examines Web visibility in real time and evaluates the performance of the proposed content of information. CAWIS allows an exploratory and open way for building information channels and improving the visibility of product manufacturers on the Web.     

Distinguishing the effects of B2B information quality,system quality,and service outcome quality on trust and distrust

Successful business-to-business (B2B) data exchanges can help firms improve inter-organizational cooperation and operational practices, thereby increasing competitive advantage. However, data exchange quality and trust are not assured. Further, although researchers have examined how trust in the exchange partner relates to data exchange system success, both trust and distrust may be important to consider. Using two-factor theory and trust theory, we examine the differential impacts of information quality, system quality, and service outcome quality on trusting and distrusting beliefs. We also study whether trusting and distrusting beliefs have differential influences on relationship commitment and perceived risk. Results from a laboratory experiment show that information quality, a process (i.e., motivating) factor, more strongly influences trusting beliefs than distrusting beliefs, whereas service outcome quality, an outcome (i.e., hygiene) factor, more strongly influences distrusting beliefs. Also, while trusting beliefs has a significantly stronger influence on relationship commitment, trusting and distrusting beliefs have equivalent effects on perceived risk. Implications and ways to expand this research are discussed.     

Customer complaints monitoring with customer review data analytics: An integrated method of sentiment and statistical process control analyses

This study presents a data-driven method to monitor customer complaints for efficient service quality management. Recognising the value of customer reviews as a pool of 'voice of the customer', we propose an integrated method of sentiment and statistical process control analyses. The use of customer review data for statistical process control analysis extends the scope of research and application from the supplier perspective to customer-centric service quality management. The sentiment analysis enables systematic identification of a customer satisfaction score from customer review data while the statistical process control chart analysis allows early detection of significant customer complaints and prevents service failures. The integration of two analyses makes it possible to monitor customer complaints at acceptable time and cost. We applied and validated the proposed method using a mobile game service, offering a guideline for its implementation and customisation. The proposed method is expected to be used as an effective tool for customer complaints monitoring over time, which enables responsive and preventive quality management.     

An exploration of risk information search via a search engine: Queries and clicks in healthcare and information security

The general public is increasingly using search engines to seek information on risks and threats. Based on a search log from a large search engine, spanning three months, this study explores user patterns of query submission and subsequent clicks in sessions, for two important risk related topics, healthcare and information security, and compares them to other randomly sampled sessions. We investigate two session-level metrics reflecting users' interactivity with a search engine: session length and query click rate. Drawing from information foraging theory, we find that session length can be characterized well by the Inverse Gaussian distribution. Among three types of sessions on different topics (healthcare, information security, and other randomly sampled sessions), we find that healthcare sessions have the most queries and the highest query click rate, and information security sessions have the lowest query click rate. In addition, sessions initiated by the users with greater search engine activity level tend to have more queries and higher query click rates. Among three types of sessions, search engine activity level shows the strongest effect on query click rate for information security sessions and weakest for healthcare sessions. We discuss theoretical and practical implications of the study.     

Reading to make a decision or to reduce cognitive dissonance? The effect of selecting and reading online reviews from a post-decision context

This research challenges the presumption that reading online reviews solely affect reader attitudes toward a prospective decision. Instead, readers may strategically select and read reviews after a decision. This research advances and tests hypotheses proposing that: (1) post-decision readers select decision-supportive reviews earlier and more frequently; and (2) the reviews they read affect the subsequent cognitive dissonance they experienced. Two studies employed an original post-decision experiment and demonstrated that readers expressed biased review selection. Interestingly, the reviews they read affected and increased their cognitive dissonance. The findings contributed to understanding the complex dynamic of online reviews in a post-decision context.     

Cytofluid dynamic theory of the origin of base, information, and function

On the basis of the first principle of continuum mechanics, we clarify an essential and artistic principle promoting the origin of transfer RNA (tRNA) molecules, i.e., the origin of information and function. It should be stressed that the ladder of asymmetry with artistic ratios of about 2∶3, such as the golden and silver ratios, is the essential prerequisite for the autocatalytic production of tRNA with a two-dimensional clover structure. This work was presented, in part, at the Sixth International Symposium on Artificial Life and Robotics, Tokyo, Japan, January 15–17, 2001     

Impact of information quality and decision-maker quality on decision quality: a theoretical model and simulation analysis

The impact of information technology (IT) on firm performance is widely studied but little understood. A common perception is that IT improves the quality of information, which, in turn, improves decision quality and performance. Several studies of IT-performance relationship have used managers' perceived as opposed to actual performance. We investigate the impact of information quality and decision-maker quality on actual decision quality using a theoretical and a simulation model. We use accuracy as the measure of quality. Our analysis shows that, depending on the decision-maker quality, decision quality may improve or degrade when information quality improves. The decision quality improves with higher information quality for a decision-maker that has knowledge about the relationships among problem variables. However, the decision quality of a decision-maker that doesn't know these relationships may degrade with higher information quality. Simultaneous improvement in information quality and decision-maker quality results in higher decision quality. The simulation model, which relaxes some of the assumptions made by the theoretical model, yields similar results. We explain how our results supplement the results of prior studies of IT-performance relationship. Our results underscore the need for including decision-maker quality in the investigation of the IT-performance relationship and the importance of developing quality decision support tools.