The Detection of Fake Reviews in Bestselling Books: Exploration and Findings

摘要

This study detected the possible manipulation of reviews for bestseller books. The authors first used clustering analysis to identify the cluster of bestselling books and patterns of manipulated reviews and ratings. They then used an artificial neural network to predict the possibility of review manipulation in bestselling books based on the patterns identified. The prediction outcome has an accuracy rate of 89%. They found that fake or manipulated reviews for bestselling books could be identified by analyzing abnormal rating fluctuations. The findings could help e-commerce platforms identify review manipulations and thereby help customers make prudent purchase decisions.