Sentiment analysis is the process of extracting sentiments from data and is used to monitor the popularity of products, brands, services, and individuals. While sentiment analysis has been extensively applied to languages like English and Chinese over the past decade, languages such as Urdu and Hindi have largely been overlooked by the research community. This article introduces a machine learning approach for sentiment analysis in Urdu. The data was collected from various blogging websites and annotated by human experts. Four widely recognized supervised machine learning classifiers—Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naive Bayes, and Multinomial Logistic Regression (MLR)—were employed to classify sentiments from the preprocessed data. The results were meticulously analyzed and compared, revealing that KNN outperformed the other classifiers, achieving an accuracy of 92% on the test dataset.