Low-Quality Product Review Detection in Opinion Summarization

TLDR

Product reviews posted at online shopping sites vary greatly in quality. The study aims to detect low‑quality product reviews and improve opinion summarization by applying a classification‑based approach. The authors define quality specifications and employ a classification‑based model in a two‑stage framework to detect low‑quality reviews. The study identifies three biases in current review evaluation standards and demonstrates that the classification model effectively discriminates low‑quality reviews and improves opinion summarization.

Abstract

Product reviews posted at online shopping sites vary greatly in quality. This paper addresses the problem of detecting lowquality product reviews. Three types of biases in the existing evaluation standard of product reviews are discovered. To assess the quality of product reviews, a set of specifications for judging the quality of reviews is first defined. A classificationbased approach is proposed to detect the low-quality reviews. We apply the proposed approach to enhance opinion summarization in a two-stage framework. Experimental results show that the proposed approach effectively (1) discriminates lowquality reviews from high-quality ones and (2) enhances the task of opinion summarization by detecting and filtering lowquality reviews.