Impact of social media posts’ characteristics on movie performance prior to release: an explainable machine learning approach

Abstract

In the era of invasive social media and advanced artificial intelligence, sentiment analysis has become a vital tool for e-commerce and businesses to grasp user needs and monitor brand perception. This is particularly relevant in the film industry, where understanding the determinants of a movie’s pre-release performance is crucial for producers and investors. Traditional methods often rely on complex algorithms that lack transparency in elucidating the relationship between key risk factors and movie outcomes. This study addresses this gap by employing an explainable analytics framework to investigate the impact of various social media post characteristics on movie performance before its release. Initially, an exploratory data analysis was undertaken to identify significant risk factors associated with movie failures. Subsequently, the study segmented the analysis into three risk categories—low, moderate, and high risk—and applied conventional machine learning models to forecast the likelihood of failure within each category. The culmination of this research involved the application of a SHapley Additive exPlanation (SHAP) model, which provided insightful interpretations of how different risk factors contribute to the potential success or failure of movies. By integrating SHAP for interpretability, this research offers novel insights into the predictive dynamics of movie performance, paving the way for informed decision-making in the film industry.