Detecting Sockpuppets in Deceptive Opinion Spam
This work addresses the issue of deceptive online reviews for platforms and users, but it appears incremental as it builds on existing authorship attribution techniques.
The paper tackles the problem of detecting sockpuppets in deceptive opinion spam by proposing two methods: a feature subsampling scheme using KL-Divergence and a transduction scheme called spy induction. Experiments with ground truth data demonstrate the effectiveness of these approaches.
This paper explores the problem of sockpuppet detection in deceptive opinion spam using authorship attribution and verification approaches. Two methods are explored. The first is a feature subsampling scheme that uses the KL-Divergence on stylistic language models of an author to find discriminative features. The second is a transduction scheme, spy induction that leverages the diversity of authors in the unlabeled test set by sending a set of spies (positive samples) from the training set to retrieve hidden samples in the unlabeled test set using nearest and farthest neighbors. Experiments using ground truth sockpuppet data show the effectiveness of the proposed schemes.