共查询到20条相似文献，搜索用时 687 毫秒
1.
《Information processing & management》2019,56(4):1234-1244
The impact of online reviews on businesses has grown significantly during last years, being crucial to determine business success in a wide array of sectors, ranging from restaurants, hotels to e-commerce. Unfortunately, some users use unethical means to improve their online reputation by writing fake reviews of their businesses or competitors. Previous research has addressed fake review detection in a number of domains, such as product or business reviews in restaurants and hotels. However, in spite of its economical interest, the domain of consumer electronics businesses has not yet been thoroughly studied. This article proposes a feature framework for detecting fake reviews that has been evaluated in the consumer electronics domain. The contributions are fourfold: (i) Construction of a dataset for classifying fake reviews in the consumer electronics domain in four different cities based on scraping techniques; (ii) definition of a feature framework for fake review detection; (iii) development of a fake review classification method based on the proposed framework and (iv) evaluation and analysis of the results for each of the cities under study. We have reached an 82% F-Score on the classification task and the Ada Boost classifier has been proven to be the best one by statistical means according to the Friedman test. 相似文献
2.
《Information processing & management》2020,57(5):102221
Although statistical learning methods have achieved success in e-commerce platform product review sentiment classification, two problems have limited its practical application: 1) The computational efficiency to process large-scale reviews; 2) the ability to continuously learn from increasing reviews and multiple domains. This paper presents a continuous naïve Bayes learning framework for large-scale and multi-domain e-commerce platform product review sentiment classification. While keeping the high computational efficiency of the traditional naïve Bayes model, we extend the parameter estimation mechanism in naïve Bayes to a continuous learning style. We furthermore propose ways to fine-tune the learned distribution based on three kinds of assumptions to better adapt to different domains. Experimental results on the Amazon product and movie review sentiment datasets show that our model can use the knowledge learned from past domains to guide learning in new domains, and has a better capacity of dealing with reviews that are continuously updated and come from different domains. 相似文献
3.
在线商品虚假评论信息不仅误导消费者购物决策与商家销售评估,而且严重干扰了在线商品交易平台的意见挖掘结果。本文针对国内外对在线商品虚假评论治理的研究现状,从法律监管和鉴别模型两个层面重新定位了其治理目标,指出应根据不同的治理对象,从监管虚假评论形成路径的基本要素、减弱虚假评论形成路径的促进因素、激励正常消费者作出真实有效的评论并优化虚假评论识别模型的鉴别准确率4个方面完善在线商品虚假评论信息的治理途径,并详细阐述了各治理途径的具体实施办法以及今后优化和完善的建议与对策。 相似文献
4.
《International Journal of Information Management》2017,37(3):202-213
Due to the proliferation of Web 2.0 technology, e-commerce has evolved into social commerce. In this social commerce era, consumers are increasingly dependent on each other and look for social support (informational and emotional) online even before making purchases. This study examines the content of consumer reviews, a fundamental construct of social commerce. Topics expressed in consumer reviews (collected from Amazon.com) are explored using a machine learning technique (i.e. latent semantic analysis). This study documents the thematic differences between positive and negative reviews and finds that negative reviews report service-related failures while positive reviews relate more to the product, among other things. Next, the informational support aspect of social commerce is explored by identifying the topics expressed in reviews that are helpful in purchase decisions. The findings demonstrate that potential customers (i.e. those who would like to purchase a product in the near future and currently are reading reviews with the intention to decide whether or not to buy that product) find the negative reviews containing service failure information and the positive reviews containing information on core functionalities, technical aspects, and aesthetics to be more helpful. Theoretical and managerial implications are discussed. 相似文献
5.
以淘宝为例,通过对43万条评论语料进行分析以及乔装淘宝店主获取的事实数据,从在线商品虚假评论实际解决需要出发,为在线商品虚假评论界定了新的含义,归纳了在线商品虚假评论的影响,最后全面分析了由在线评论者、在线销售商家、在线商品交易平台、虚假评论中介四大主体所组成体系中在线商品虚假评论的六大形成路径、形成动因及特点.本文对下一步的在线商品虚假评论识别技术等相关研究有极强的理论和实践指导意义. 相似文献
6.
《Research Policy》2019,48(8):103744
Involving customers is often considered a method to develop products in line with market needs. However, we still need to obtain more insights into the respective drivers and outcomes in the context of (a) the involvement of customers by entrepreneurial ventures and (b) business-to-consumer (B2C) relationships. This study suggests that reward-based crowdfunding can provide a digital opportunity for both areas. We explore how community-derived social capital influences ventures’ approach to engaging backers in new product development and how this, in turn, advances product innovativeness. Using structural equation modeling, we test a unique dataset that combines primary survey and secondary platform data from 710 crowdfunding ventures. Our results provide a nuanced picture of how social capital dimensions are associated with backers as an information source and as co-developers and, indirectly, with new product innovativeness. This study underscores that crowdfunding serves as a digital platform for market-oriented innovation. It contributes empirical insights into how nascent teams can engage the digital crowd in product development via crowdfunding. We also add to social capital literature by illuminating web-mediated mechanisms that transform knowledge into tangible innovation outcomes. 相似文献
7.
【目的/意义】消费者评论数量巨大且充满随意性,因此需要对评论信息进行分析,信息分析可以给潜在消
费者提供有价值参考,可以给商家提供消费者对产品的反馈意见,也可以给平台改善服务提供参考,从而实现消费
者、商家和平台的共赢。【方法/过程】以从京东商城爬取的部分产品评论文本为研究对象,使用词频、词云分析的方
法对评论中的产品特征进行抽取,分析消费者对产品属性的偏好,通过情感倾向计算方法,对五种不同类别的产品
评论进行情感倾向分析,并研究消费者对产品属性的偏好和情感倾向间的关系。【结果/结论】研究结果表明,对于
不同类型的产品,消费者有不同的属性偏好,且关注的产品特征数量也不同。在此基础上,分别对商家、电商平台
和消费者提出了有针对性的建议。【创新/局限】使用评论挖掘的方法,从消费者、商家和平台三个视角进行研究,提
出应对方法。但对数据的处理仍然不够精确,有待进一步研究。 相似文献
8.
9.
【目的/意义】在线评论在消费者购买决策中的重要性日益凸显,探索电商平台消费者绿色产品在线评论信息采纳的影响因素,为进一步挖掘在线评论的商业价值、促进绿色产品的消费提供参考。【方法/过程】以TAM和ELM为理论基础,结合社会环境因素和消费者个体特质因素,构建电商平台消费者绿色产品在线评论信息采纳意愿的影响因素模型,运用结构方程模型进行实证检验。【结果/结论】结果表明评论质量和社会影响均对感知评论有用性产生正向影响,评论源可信度与感知评论有用性的关系不显著,感知评论有用性和社会影响又对评论采纳意愿产生正向影响,产品卷入度会调节消费者评论有用性的感知,而专业知识未能起到调节作用。 相似文献
10.
品牌建设贯穿农业全产业链，是推动农业农村高质量发展的持久动力，但发端于网购、成长于网购的特色农产品网货品牌还较少受到学者关注。本文采用双案例研究方法，首先提出了整合品牌定位理论、品牌叙事理论和电商运营理论的农产品网货品牌培育节俭式创新理论框架，然后利用研究假设对“夔山里二娃子”和“小七陈卤”两个来自草根创业的农产品网货品牌进行了案例分析研究。研究发现互联网嵌入为农产品网货品牌节俭式创新创造了机遇，精准定位帮助农产品网货品牌占领消费者心智，品牌故事是农产品网货品牌与消费者之间的情感纽带，体验口碑是农产品网货品牌持续成长的动力。本文的结论丰富了网货品牌培育机理的理论认识，对于区域农产品电商产业发展、农产品电商草根创业者如何建立“大品牌”实践路径具有一定参考价值。 相似文献
11.
Ideation is an important phase in the new product development process at which product designers innovate and select novel ideas that can be added as features to an existing product. One way to find novel ideas is to transfer uncommon features of products of other domains and integrate them into the product to be improved. However, before incorporating such targeted features into the product, they need to be evaluated against the customers’ acceptance in social media using sentiment aggregation tools. Despite the many studies in sentiment analysis, mapping the customers’ opinions towards both high-level and technical features of a product extracted from social media to their best corresponding component in that product is still a challenge. Furthermore, none of the existing approaches ascertains the sentiment value of a targeted feature by capturing its dependencies on other features. In this paper, to address these drawbacks, we propose the sentiment aggregation framework for targeted features (SA-TF). SA-TF determines the sentiment of a targeted feature by assisting product designers in the tasks of mapping the features discussed in the reviews to the right product components, sentiment aggregation and considering feature dependencies to determine their polarity. The superiority of the different phases of SA-TF is demonstrated with experiments and comparing it with an existing approach. 相似文献
12.
13.
14.
The paper aims at analysing the relationship between the market extension of Knowledge-Intensive Business Services (KIBS) and their knowledge management strategies. The literature emphasizes the strong relationship existing between KIBS and their customers in terms of innovation process and knowledge creation. We argue that the knowledge management strategies – in terms of knowledge codification, personalization, and knowledge creation – implemented by a KIBS is related to their geographical market extension. A quantitative approach is developed based on more than 150 Italian KIBS specializing in design and communication. The paper enriches the research framework concerning KIBS by emphasizing also the role of partners other than customers in KIBS’ knowledge management strategies. 相似文献
15.
介绍了电子商务的分类及WebServices的技术优势,通过对茶产业电子商务应用平台的功能需求进行分析,给出了基于WebServices的电子商务系统体系结构框架。 相似文献
16.
《Information processing & management》2020,57(6):102323
With the fast growth of e-commerce and the emerging new retail trend—online and offline integration—it is important to recognize the target market and satisfy customers with different needs by analyzing their online search behaviors. Accordingly, we propose sequential search pattern analysis and clustering to analyze consumers’ search behavior throughout the entire shopping process from the perspective of consumer need-states. We seek to understand how recommendation functions (RFs) or popular non-RF web features help consumers to shop online from a need-state perspective. We adopt maximal repeat patterns (MRPs) and lag sequential analysis (LSA) to analyze the sequence of search paths and identify significant repeated search patterns. Furthermore, to investigate the behaviors of customers with different types of need-states, we analyze webpages related to RFs and non-RF features using clustering to connect the evaluation results of search patterns with page traversal behaviors. This yields four groups of consumers who browse for information, adopt recommendations, consult reviews, and conduct searches with different levels of goal-oriented or exploratory-based need-states. The results show that consumers with strong goal-oriented need-states have the simplest search paths compared to other groups, whereas exploratory-based consumers have the most complicated search paths. Furthermore, consumers with higher need-states tend to search directly, consult reviews carefully, and have stored sequential search patterns, whereas consumers with exploratory-based need-states tend to explore the categories of products and adopt product classification hierarchy as a pivot to explore web features and then adopt specific types of RFs. Interestingly, consumers in the review-consulting group all belong to the goal-oriented need-states type with strong knowledge-building behaviors compared to others. The results reveal that each group employs its own particular web features to facilitate the shopping process and we can identify consumer types based on shopping behavior in the early stage of shopping. This suggests that e-store sellers can refine web features and deploy marketing strategies tailored to the search patterns for different levels of need-states. 相似文献
17.
Blockchain technology provides us a new tool to solve the product traceability problem in supply chain management. This research focuses on the cross-border e-commerce context, to propose a blockchain-based framework, and develop a set of corresponding techniques and methods for achieving traceable products and transactions in supply chain management. A general blockchain-based product traceability framework is introduced. This framework is based on a cross-border e-commerce supply chain context, incorporating a series of blockchain-based models, including multi-chain structure model, data management model and block structure model. Several core methods and algorithms are also developed, such as information anchoring method, key distribution method, information encryption algorithm and anti-counterfeiting method. The framework, models and methods form a complete and comprehensive solution, which are evaluated by applying to several typical problems and attack cases. The case analysis results show that the framework, models and methods can successfully deal with key recover problem, and protect against clone attack, counterfeit tag attack and counterfeit product attack. The effectiveness, extendibility, security, implementation and governance issues of applying these solutions are also discussed. This research contributes to the theoretical and practical literatures on blockchain technology, cross-border e-commerce and supply chain management research fields. 相似文献
18.
《Information processing & management》2019,56(3):823-843
A vast number of user opinions are available from reviews posted on e-commerce websites. Although these opinions are a valuable source of knowledge for both manufacturers and customers, they provide volumes of information that exceeds the human cognitive processing capacity, which can be a major bottleneck for their effective use. To address this problem, a number of opinion-summarization methods have been proposed to organize these opinions by grouping them around aspects. However, these methods tend to generate an excessive number of aspect groups that are frequently overly generic and difficult to interpret. We argue that a superior alternative would be to organize opinions around product attributes as defined in a product catalog. Typically, product attributes correspond to the most important characteristics of the products. Furthermore, they are common to all products in a given category and thus, form a more stable set than aspects. In this paper, we propose a novel approach called OpinionLink to products in a catalog at the attribute granularity level with opinions extracted from product reviews. The proposed approach is divided into two phases. In the first phase, OpinionLink uses a classifier to identify opinionated sentences in the reviews on a particular product. In the second phase, another classifier is used to map the opinions that were previously extracted from the user reviews to the attributes of the products in the product catalog. We performed a series of experiments on these phases. For the first phase, our experiments indicated that using classifiers with the proposed features achieved an average of 0.87 in terms of F1 measure for the task of identifying opinionated sentences. In the second phase, the method we proposed for the opinion-mapping task achieved an average of 0.85 in terms of F1. Further, we verified the effectiveness of the proposed approach as a realistic end-to-end application, indicating that we can use OpinionLink in a real setting. Finally, we empirically demonstrate the feasibility of using the proposed approach with an extremely large volume of opinions available in a collection of more than 600,000 real reviews. We also set forth a number of directions for future research. 相似文献
19.
【目的/意义】为了完善电子商务信用体系,优化电子商务环境,提高电子商务活动的安全性,提出基于区块链技术的在线电子商务信用信息共享方法。【方法/过程】本文首先构建了在线电子商务信用信息共享平台构架,通过将数字区块链技术和交易区块链技术融入到在线电子商务信用信息共享平台中,由数字区块链技术完成数据信息预处理过程,并利用拜占庭容错机制构建共识模型,保障在线电子商务信用信息共享平台的稳定性;由交易区块链技术中的盲签名算法提高信用信息的安全性和共享效率,实现电子商务信用信息的共享。最后,通过对比实验,对所提出的电子商务信用信息共享方法进行测试。【结果/结论】实验结果表明,所提方法的通信开销小、吞吐量高、时延小、安全性高、实用性强。【创新/局限】由于本文未结合实际案例对所提方法进行验证,研究结论具有一定局限性,因此今后需进一步深究与探讨。 相似文献
20.
Studies on knowledge management have generated an awareness that it is fundamentally important for small- and medium-sized enterprises (SMEs) to be able to exploit sources of knowledge outside the firm by means of external relationships, but this understanding has not been followed up by an adequate theoretical and empirical research effort to analyse the role of relationships in an SME’s knowledge management processes. The present contribution first sketches this gap on the grounds of the available literature reviews. Then it proposes a framework – focusing the concept of absorptive capacity – with a view to filling this theoretical gap. Finally, based on the proposed framework, two specific topics of considerable importance to SMEs are discussed: (i) how capabilities are developed in the start-up phase of a new venture; and (ii) knowledge processes in geographical clusters. 相似文献