Sentiment analysis of youtube comments on the palestine-israel conflict: Performance comparison of SVM, KNN, and RFC

The Palestine-Israel conflict, rooted in territorial and religious identity disputes in the Middle East, notably over the sanctity of Jerusalem, is impacted by various political, economic, and social factors. This study employs text-mining techniques to analyze the sentiment of YouTube comments concerning the conflict. Utilizing data collected via the YouTube API, the study preprocesses, analyzes sentiment, and classifies comments using three machine learning algorithms: K-Nearest Neighbors (K-NN), Random Forest Classifier (RFC), and Support Vector Machine (SVM). The categorization report measures are utilized to compare how well the models performed in classifying estimation as positive or negative. Outflanking all other classifiers, the Irregular Woodland Classifier (RFC) accomplishes 78curacy with accuracy rates of 0.76 for positive and 0.79 for negative assumptions. With a precision rate of 77%, SVM illustrates an inclination in favor of negative sentiments, though K-NN, with an exactness rate of 60%, shows an imbalance favoring negative over positive estimations.