Identifying fake Amazon reviews as learning from crowds

Customers who buy products such as books online often rely on other customers reviews more than on reviews found on specialist magazines. Unfortunately the confidence in such reviews is often mis-placed due to the explosion of so-called sock puppetry–authors writing glowing reviews of their own books. Identifying such deceptive reviews is not easy. The first contribution of our work is the cre-ation of a collection including a number of genuinely deceptive Amazon book re-views in collaboration with crime writer Jeremy Duns, who has devoted a great deal of effort in unmasking sock puppet-ing among his colleagues. But there can be no certainty concerning the other re-views in the collection: all we have is a number of cues, also developed in collab-oration with Duns, suggesting that a re-view may be genuine or deceptive. Thus this corpus is an example of a collection where it is not possible to acquire the actual label for all instances, and where clues of deception were treated as anno-tators who assign them heuristic labels. A number of approaches have been proposed for such cases; we adopt here the ‘learn-ing from crowds ’ approach proposed by Raykar et al. (2010). Thanks to Duns ’ cer-tainly fake reviews, the second contribu-tion of this work consists in the evaluation of the effectiveness of different methods of annotation, according to the performance of models trained to detect deceptive re-views. 1