The paper proposes a sentiment analysis model based on BERT and XLNet for movie reviews. Movie reviews are a valuable source of information for potential viewers, but reading all of them can be time-consuming. Sentiment analysis can extract subjective information such as the overall opinion, strengths, weaknesses, and recommendations of the reviewer, helping viewers make informed decisions. XLNet and BERT are advanced pre-trained language models that learn bidirectional relationships between words, improving performance on natural language processing tasks. The experiment uses the Internet Movie Database (IMDB) Dataset and the Rotten Tomatoes dataset, pre-processing both datasets to enhance baseline technique results. The results show that XLNet achieved the highest accuracy on both datasets. The research highlights how sentiment analysis can provide insights into the emotions and attitudes expressed in movie reviews, aiding in predicting a movie's performance based on its overall sentiment.The paper proposes a sentiment analysis model based on BERT and XLNet for movie reviews. Movie reviews are a valuable source of information for potential viewers, but reading all of them can be time-consuming. Sentiment analysis can extract subjective information such as the overall opinion, strengths, weaknesses, and recommendations of the reviewer, helping viewers make informed decisions. XLNet and BERT are advanced pre-trained language models that learn bidirectional relationships between words, improving performance on natural language processing tasks. The experiment uses the Internet Movie Database (IMDB) Dataset and the Rotten Tomatoes dataset, pre-processing both datasets to enhance baseline technique results. The results show that XLNet achieved the highest accuracy on both datasets. The research highlights how sentiment analysis can provide insights into the emotions and attitudes expressed in movie reviews, aiding in predicting a movie's performance based on its overall sentiment.