Conducting a comparative study of real-time sentiment analysis poses a significant challenge due to the continuous variation in individuals' accents and the difficulty in quantifying them. In computer science, specifically supervised machine learning classifiers, researchers face the obstacle of lacking direct observation. This study explores the performance of well-known supervised machine learning classifiers such as SVM, K-SVM, and Multinomial Naïve Bayes. We utilize a comprehensive corpus of real-time Twitter tweets and news blogs related to disputed territories. These classifiers are trained on the Kaggle dataset for real-time sentiment analysis to achieve the highest accuracy and subsequently tested on real-time data. Notably, the kernel support vector machine performs better in real-time data, as evidenced by the substantial proportion of positive sentiments detected. Furthermore, our study offers a pathway for young scholars to assess the real-time sentiment correlation between corresponding countries, enabling predictions of potential conflicts that may lead to significant casualties.