Review Helpfulness Assessment based on Convolutional Neural Network
This work addresses the problem of filtering helpful reviews for online platforms, but it is incremental as it applies an existing CNN architecture to a new domain with modest gains.
The paper tackles the problem of assessing online review helpfulness by implementing a convolutional neural network (CNN), achieving improvements of 2.5% accuracy with text-only models and 4.24% with combined text and rating information compared to traditional methods.
In this paper we describe the implementation of a convolutional neural network (CNN) used to assess online review helpfulness. To our knowledge, this is the first use of this architecture to address this problem. We explore the impact of two related factors impacting CNN performance: different word embedding initializations and different input review lengths. We also propose an approach to combining rating star information with review text to further improve prediction accuracy. We demonstrate that this can improve the overall accuracy by 2%. Finally, we evaluate the method on a benchmark dataset and show an improvement in accuracy relative to published results for traditional methods of 2.5% for a model trained using only review text and 4.24% for a model trained on a combination of rating star information and review text.