Detection of Review Abuse via Semi-Supervised Binary Multi-Target Tensor Decomposition
This addresses review fraud in e-commerce, which influences buying decisions, but the approach is incremental as it builds on existing tensor decomposition methods with semi-supervision.
The paper tackles the problem of detecting abusive sellers and reviewers in e-commerce reviews by applying a semi-supervised binary multi-target tensor decomposition method, achieving higher precision and recall compared to unsupervised techniques.
Product reviews and ratings on e-commerce websites provide customers with detailed insights about various aspects of the product such as quality, usefulness, etc. Since they influence customers' buying decisions, product reviews have become a fertile ground for abuse by sellers (colluding with reviewers) to promote their own products or to tarnish the reputation of competitor's products. In this paper, our focus is on detecting such abusive entities (both sellers and reviewers) by applying tensor decomposition on the product reviews data. While tensor decomposition is mostly unsupervised, we formulate our problem as a semi-supervised binary multi-target tensor decomposition, to take advantage of currently known abusive entities. We empirically show that our multi-target semi-supervised model achieves higher precision and recall in detecting abusive entities as compared to unsupervised techniques. Finally, we show that our proposed stochastic partial natural gradient inference for our model empirically achieves faster convergence than stochastic gradient and Online-EM with sufficient statistics.