The competitive airline sector has grown at a breakneck pace in the last two decades. A useful source for collecting consumer feedback and performing various forms of analysis on it is proper data collection. This collection of data can be used for sentiment analysis. Sentiment analysis is a type of analysis that involves extracting sentiment to find attitudes and emotions associated with the text or data supplied. It's a classification approach in which machine learning techniques are used to identify positive and negative words or reviews in text-driven databases. Further to explain the reasons for negative comments, a word cloud and a bar graph are used. Sentiment analysis is used to analyze the Airline reviews dataset in this paper. To test the performance of sentiment analysis, many Machine Learning (ML) algorithms have been utilized, such as Naive Bayes, Support Vector Machine, and Decision Tree (DT), and each of these approaches has produced distinct results. The performance of Google's BERT algorithm has been evaluated to that of other machine learning algorithms in our research. Furthermore, this paper explores the Bert architecture, which has been pre-trained on two NLP tasks: Masked language modeling and Sentence prediction. The ”Random Forest” is used as a baseline against which the results of the ”BERT Model” are compared because its performance is the best among the machine learning models. In terms of performance criteria such as accuracy, precision, recall, and F1-score, it is discovered that BERT outperformed the other ML techniques.