User Bias Removal in Review Score Prediction

TL;DR

This paper introduces two statistical methods to reduce user bias noise in review score prediction models, using a single global classifier, leading to improved accuracy on Amazon review datasets.

Contribution

It presents novel simple statistical techniques for bias removal in review score prediction, avoiding multiple classifiers per user.

Findings

Improved review score prediction accuracy across datasets

Effective bias removal with simple statistical methods

Consistent results across different text feature representations

Abstract

Review score prediction of text reviews has recently gained a lot of attention in recommendation systems. A major problem in models for review score prediction is the presence of noise due to user-bias in review scores. We propose two simple statistical methods to remove such noise and improve review score prediction. Compared to other methods that use multiple classifiers, one for each user, our model uses a single global classifier to predict review scores. We empirically evaluate our methods on two major categories (\textit{Electronics} and \textit{Movies and TV}) of the SNAP published Amazon e-Commerce Reviews data-set and Amazon \textit{Fine Food} reviews data-set. We obtain improved review score prediction for three commonly used text feature representations.