Sentiment Analysis of Public Opinion on the Palestinian-Israeli Conflict using Support Vector Machine and Naïve Bayes Algorithms

The Palestinian-Israeli conflict, particularly in Rafah City, Gaza Strip, has drawn global attention due to escalating violence, prompting widespread responses on X social media. This study analyses public sentiment on the topic ‘Eyes on Rafah’ using 403 tweets, with 306 classified as positive and 94 as negative. This study aims to analyse the world's response to the prolonged conflict To evaluate these sentiments, Text Mining techniques were applied, comparing the performance of Support Vector Machine (SVM) and Naïve Bayes algorithms. SMOTE optimisation was implemented to address data imbalance and enhance algorithm performance. Findings reveal that the SVM algorithm achieved superior results with 97% accuracy, precision of 97%, recall of 100%, and F1-Score of 98%, compared to Naïve Bayes with 86% accuracy, precision of 100%, recall of 75%, and F1-Score of 85%. These results highlight the effectiveness of SVM in analysing sentiment and the critical role of SMOTE in improving classification accuracy for both algorithms.