Intelligent Age Group Classification System for Animated Films Using Hybrid Machine Learning Models

Age-appropriate content classification in animated films presents a significant challenge in content management and recommendation systems. This paper proposes a comprehensive framework for automated age group classification of animated films using multiple machine learning approaches. We evaluated seven traditional machine learning models (Decision Tree, Random Forest, Logistic Regression, SVM, Gradient Boosting, KNN, and Naive Bayes) and a deep learning architecture on a dataset of animated films, considering nine key features including production attributes and content characteristics. The models were trained to classify films into Child (< =6 years), Pre-Teen (7–10 years), Teen (11–14 years), and Youth (>14 years) categories. Feature importance analysis revealed that Educational Content (19.01 %), Duration (17.53%), and Release Year (14.98%) were the most significant predictors. The Support Vector Machine and K-Nearest Neighbors classifiers achieved the highest accuracy of 59%, while the deep learning model demonstrated comparable performance with 57 % accuracy. All models demonstrated significant accuracy in identifying animated films targeted at viewers aged 6 and above, compared to other age categories. This research provides insights into machine learning approaches for classifying age groups in animated films and examines the challenges of multi-classification for visual content.