This study investigates the impact of online review helpfulness and electronic word-of-mouth (eWOM) on box office revenue prediction. Using data from the Korean movie market (Naver Movies), the study employs machine learning methods (random forest, boosted decision trees, k-nearest neighbor, discriminant analysis) to compare prediction performance between subsamples of movies with high and low review/reviewer helpfulness. Results indicate that movies with more helpful reviews or reviewers exhibit improved prediction accuracy, suggesting review and reviewer helpfulness are crucial moderators enhancing the predictive power of eWOM for box office revenue.
Publisher
Humanities and Social Sciences Communications
Published On
Sep 07, 2020
Authors
Sangjae Lee, Joon Yeon Choeh
Tags
online reviews
helpfulness
box office revenue
eWOM
machine learning
Related Publications
Explore these studies to deepen your understanding of the subject.
