A Tangled Web: Evaluating the Impact of Displaying Fraudulent Reviews

摘要: The growing interest in social media for legitimate promotion has been accompanied by an increasing number of fraudulent reviews. Beyond fraud detection, little is known about what review portals should do with reviews after detecting them. In this paper, we study how consumers respond to potentially and can leverage such knowledge design better management policies. To so, combine randomized experiments statistical learning using large-scale archival data from Yelp. Our show that tend expand the variety their choice set during product search increase trust towards portal when it displays along non-fraudulent reviews, rather than censor information. Finally, our analysis a Maximum Likelihood Estimation method allows us novel fraud-awareness reputation system platforms deploy improve consumer decision making. Displaying Fraudulent Reviews