This study aims to conduct sentiment analysis on reviews of the film "Dirty Vote" from various sources, including social media, film review websites, and online forums, using a fine-tuned BERT model. The research involves data collection, preprocessing, BERT model refinement, and model performance evaluation. The results show that the BERT model achieves high performance with accuracy, precision, recall, and F1-score exceeding 0.8 on the validation dataset. Sentiment analysis from various sources reveals variations in public opinion toward the film, with significant differences in sentiment expressed via social media compared to reviews from dedicated websites or online forums. Discussion of sentiment findings reveals people's preferences for certain aspects of films, such as visual effects and music. Sentiment analysis results show that visual effects and music received the highest ratings, while the cast and director received lower ratings. This information can be used by filmmakers to improve unsatisfactory aspects in future film production. The study also highlights the effectiveness of BERT in sentiment analysis, demonstrating its potential in understanding public opinion and responses in text. The research contributes to the development of sentiment analysis methods using BERT for film reviews, providing insights into public perception and offering guidance for future film production.This study aims to conduct sentiment analysis on reviews of the film "Dirty Vote" from various sources, including social media, film review websites, and online forums, using a fine-tuned BERT model. The research involves data collection, preprocessing, BERT model refinement, and model performance evaluation. The results show that the BERT model achieves high performance with accuracy, precision, recall, and F1-score exceeding 0.8 on the validation dataset. Sentiment analysis from various sources reveals variations in public opinion toward the film, with significant differences in sentiment expressed via social media compared to reviews from dedicated websites or online forums. Discussion of sentiment findings reveals people's preferences for certain aspects of films, such as visual effects and music. Sentiment analysis results show that visual effects and music received the highest ratings, while the cast and director received lower ratings. This information can be used by filmmakers to improve unsatisfactory aspects in future film production. The study also highlights the effectiveness of BERT in sentiment analysis, demonstrating its potential in understanding public opinion and responses in text. The research contributes to the development of sentiment analysis methods using BERT for film reviews, providing insights into public perception and offering guidance for future film production.