<![CDATA[With the wide variety of film genres available, audiences often face difficulties in determining a movie’s genre solely based on its synopsis. Therefore, an automated system is needed to classify movie genres effectively. This study aims to classify movie genres based on film synopses using the Support Vector Machine (SVM) method combined with TF-IDF and N-Gram feature extraction techniques. The dataset used in this research was obtained from Kaggle and consisted of 10,000 movie records with multi-label characteristics, which were subsequently transformed into Single-label data. Four main genres were selected, namely Action, Comedy, Drama, and Horror, resulting in a final dataset of 6,000 records. The research process included data preparation, text preprocessing, TF-IDF feature extraction using unigram and bigram models, data splitting, and model evaluation. All data processing procedures were carried out in Google Colab using the Python programming language. The evaluation results indicate that the SVM model with a linear kernel achieved an accuracy of 83%. The Horror genre demonstrated the best performance, with a precision value of 91%, recall of 92%, and F1-score of 92%. These findings suggest that the combination of TF-IDF, N-Gram, and SVM provides satisfactory results for movie genre classification based on film synopses.]]>
Copyrights © 2026
