Wesly, Wesly
Unknown Affiliation

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Genre-Based Sentiment and Emotion System for Audience Insight Suwarno, Suwarno; Wesly, Wesly; Syahputra, Bayu
TIERS Information Technology Journal Vol. 6 No. 2 (2025)
Publisher : Universitas Pendidikan Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38043/tiers.v6i2.7183

Abstract

Movies can influence people’s moods in different ways depending on film genre. Fear is commonly induced by horror films, whereas joy is typically associated with comedy. Understanding how genre-based expectations shape audience emotions offers valuable insights for producers and digital platforms. However, previous studies have only briefly examined this relationship, with most focusing on general sentiment analysis. This study develops a genre-based sentiment and emotion model to analyze how film genres influence audience reactions. The Cross-Industry Standard Process for Data Mining (CRISP-DM) framework was applied to 46,173 IMDb reviews using Term Frequency–Inverse Document Frequency (TF-IDF) features and three machine learning models: Logistic Regression, Linear Support Vector Classification, and One-vs-Rest Logistic Regression. The results show that Fear (0.704) and Anger (0.684) are the most dominant emotions, indicating that audiences tend to be more emotionally engaged with intense genres. The model was also implemented in a Flask–React web-based system that allows users to analyze and visualize reviews in real time. These findings provide practical implications for filmmakers, producers, and streaming platforms in adjusting genre design, content recommendation, and promotional strategies to align with audience emotional responses.