Perbandingan Algoritma CNN Dan Naïve Bayes Dalam Analisis Sentimen Pada Twitter Terhadap Genosida Israel Ke Palestin E

The development of social media, particularly Twitter, has become a primary platform for public opinion expression on issues such as the Israeli genocide against Palestine. Manual sentiment analysis of a large volume of tweets is time-consuming, thus requiring automatic methods using machine learning. This study compares the performance of Convolutional Neural Network (CNN) and Naïve Bayes algorithms in classifying positive and negative sentiments in public opinions on this issue. Experimental results show that CNN achieves a higher accuracy of 80%, compared to 78% by Naïve Bayes. Moreover, CNN outperforms Naïve Bayes in recognizing positive sentiments, demonstrated by higher recall and f1-score values, indicating a more balanced sentiment classification. This research is expected to contribute as a reference in social media-based sentiment analysis and serve as a basis for further development of more effective sentiment classification models.