<![CDATA[Pertumbuhan jumlah penonton film yang begitu pesat mendorong industri perfilman untuk terus berinovasi, sehingga menghasilkan beragam judul baru dengan genre dan karakteristik yang semakin bervariasi. Kondisi ini menyebabkan kompleksitas data yang tinggi, sehingga dibutuhkan metode klasifikasi yang efektif dan akurat untuk mengelompokkan rating film berdasarkan karakteristiknya. Penelitian ini bertujuan untuk meningkatkan kinerja klasifikasi rating film dengan menggunakan metode ensemble soft voting, yang menggabungkan tiga algoritma klasifikasi, yaitu k-nearest neighbor (KNN), decision tree (DT), dan support vector machine (SVM). Evaluasi dilakukan dengan membandingkan kinerja metode soft voting terhadap masing-masing metode individu berdasarkan metrik akurasi, presisi, sensitivitas, dan F1-score. Hasil penelitian menunjukkan bahwa metode soft voting memberikan kinerja klasifikasi yang lebih baik dibandingkan metode KNN, decision tree, dan SVM secara terpisah, dengan capaian akurasi sebesar 89,64%, presisi 85,63%, sensitivitas 89,64%, dan nilai F1-score sebesar 86,52%.Kata kunci: klasifikasi, ensemble learning, KNN, decision tree, SVMThe rapid growth in the number of movie viewers has driven the film industry to continuously innovate, resulting in a diverse range of new titles with increasingly varied genres and characteristics. This has led to significant data complexity, necessitating an effective and accurate classification method to categorize movie ratings based on their characteristics. This study aims to evaluate the performance of the Soft Voting ensemble method in classifying movie ratings. The classification results from soft voting are compared to those of individual models, namely k-nearest neighbor (KNN), decision tree (DT), and support vector machine (SVM). The evaluation was conducted by comparing the performance of the soft voting method against each individual method based on accuracy, precision, sensitivity, and F1-score metrics. The results showed that the soft voting method provided better classification performance than the KNN, decision tree, and SVM methods individually, with an accuracy of 89.64%, a precision of 85.63%, a sensitivity of 89.64%, and an F1-score of 86.52%.Keywords: classification, ensemble learning, KNN, decision tree, SVM]]>
Copyrights © 2025
