Sentiment analysis plays a pivotal role in understanding public opinion and sentiment toward various entities, products, or events. In this study, we focus on comparing the performance metrics of two popular classification algorithms, Logistic Regression and K-Nearest Neighbors (KNN), in sentiment analysis tasks. The study utilizes a Count Vectorizer approach for feature extraction, a commonly used technique in natural language processing tasks. By employing a dataset with labeled sentiment data, we systematically evaluate the classification performance of both algorithms based on metrics such as accuracy, precision, and recall. Through this comparative analysis, we aim to provide insights into the strengths and weaknesses of each algorithm in sentiment analysis tasks, aiding practitioners in selecting the most suitable approach for their specific application scenarios.