Analisis Sentimen Ulasan Film Merah Putih: One for All Menggunakan Metode Natural Language Processing

Abstract

The Indonesian film industry has experienced significant growth in terms of production and audience numbers. However, films with nationalist themes, such as Merah Putih: One for All, face challenges in gaining popularity compared to more viral entertainment films. This study aims to analyze audience sentiment and to identify the influence of nationalism values in shaping public perception of the film. A Natural Language Processing approach was employed using the Random Forest algorithm to classify online reviews into positive, negative, and neutral categories. The data were collected from social media and digital platforms and processed using the Term Frequency–Inverse Document Frequency technique for feature representation and the Synthetic Minority Over-sampling Technique to address class imbalance. The results indicate that neutral sentiment dominates the reviews, followed by positive and negative sentiments. These findings suggest that the film is more appreciated by audience segments interested in nationalist messages, although it has not yet reached a broader audience. This study contributes to the application of data-driven sentiment analysis to support promotional strategies for national films and to better understand audience characteristics in a more comprehensive manner.