As the aviation industry evolves, understanding customer satisfaction has become critical for airlines pursuing to thrive in a competitive market. This research paper investigates the dynamics of airline customer satisfaction by analyzing reviews posted on Skytrax, a popular online platform known for its extensive collection of airline reviews. The study analyzes the essential features that are required for customer satisfaction in airline business, as well as performs a comparative analysis of various machine learning classifier algorithms by employing different metrics. The purpose of this comparison was to determine the most effective algorithm among them. The dataset utilized in the research consisted of reviews and ratings given by customers obtained through web scraping data from SkyTrax. Before data was transmitted to algorithms, data was cleaned using various techniques, data imputation, and removal of outliers, and removal of dependable and comparable features using various statistical methods. SMOTE imbalance approach was used in analyzing the level of bias in data. The study employs a range of metrics including accuracy score, precision, recall, f1-score, and confusion matrix, in order to compare different machine learning classifier algorithms, such as KNN, Random Forest, Decision Trees, and Logistics Regression, amongst others.