@conference {Ouatiti20207, title = {Towards Amazon Fake Reviewers Detection: The Effect of Bulk Users}, booktitle = {ACM International Conference Proceeding Series}, year = {2020}, note = {cited By 0}, pages = {7-12}, abstract = {Online marketplaces such as Amazon allow people to share their experiences about purchased products using textual comments known as product reviews. These reviews have become a common tool that users rely on to get insights on the quality and functionality of products and services from online consumers. However, like any other online information, reviewers raise serious questions concerning the credibility and reliability, since anyone can post reviews, which might impact the reliability of the information. This paper tackles the phenomenon of Bulk reviewers. We first analyze a large dataset of reviews from Amazon aiming to spot bulk reviewers according to their behavior. We then apply a what-if analysis to assess the effect of bulk reviews on the online marketplaces using a metric called Net Promoter Score to measure the willingness of users to recommend products. Our Results reveal that bulk users (i.e., users that review multiple times) have same distribution of ratings as non-bulk users indicating that a bulk reviewer is not automatically a fake reviewer. Yet, we discover that bulk users do inflate NPS metric and thus contribute to overestimate the level of customer satisfaction. {\textcopyright} 2020 ACM.}, keywords = {Electronic assessment, Electronic commerce, Intelligent systems, Large dataset, On-line information, On-line marketplaces, Online consumers, Product reviews, Products and services, User experience, What-if Analysis}, doi = {10.1145/3419604.3419800}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85096423765\&doi=10.1145\%2f3419604.3419800\&partnerID=40\&md5=1a79dcff298ad489f414ee1d7743d93c}, author = {Ouatiti, Y.E. and Kerzazi, N.} } @article {10115338520131101, title = {A New Feedback-Analysis based Reputation Algorithm for E-Commerce Communities.}, journal = {E-Ti: E-Review in Technologies Information}, number = {7}, year = {2013}, pages = {46 - 58}, abstract = {Dealing with the ever-growing content generated by users in the e-commerce applications, Trust Reputation Systems (TRS) are widely used online to provide the trust reputation of each product using the customers{\textquoteright} ratings. However, there is also a good number of online customer reviews and feedback that must be used by the TRS. As a result, we propose in this work a new architecture for TRS in e-commerce application which includes feedback{\textquoteright} mining in order to calculate reputation scores. This architecture is based on an intelligent layer that proposes to each user (i.e. {\guillemotleft}feedback provider{\guillemotright}) who has already given his recommendation, a collection of prefabricated feedback to like or dislike. Then the proposed reputation algorithm calculates the trust degree of the user, the feedback{\textquoteright}s trustworthiness and generates the global reputation score of the product according to his {\guillemotleft}likes{\guillemotright} and {\guillemotleft}dislikes{\guillemotright}. In this work, we present also a state of the art of text mining tools and algorithms that can}, keywords = {Algorithms, analyse de sentiment, e-commerce, Electronic commerce, La confiance, le e-commerce, le textmining, les feedback textuels, les syst{\`e}mes de r{\'e}putation, Reliability (Personality trait), Sentiment analysis, text mining, Text mining (Information retrieval), textual feedback, Trust, Trust Reputation Systems, Virtual communities}, issn = {11148802}, url = {http://search.ebscohost.com/login.aspx?direct=true\&db=iih\&AN=101153385\&site=ehost-live}, author = {Rahimi, Hasnae and El Bakkali, Hanan} }