Optimized Sentiment Analysis of Hotel Reviews using Machine Learning Algorithms

On social media, words and phrases reflect people's opinions about certain goods, services, organisations, laws, and events. In the discipline of NLP, the objective of sentiment analysis is to extract positive things or negative things from social media. Researchers are driven to complete their sentiment analysis research because of the government and corporate organisations' and individuals' exponentially growing needs. This study optimises sentimental analysis using four cutting-edge machine learning classifiers: Naivebayes, J48, BFTree, and OneR. This four classification methods' effectiveness are investigated and contrasted. While OneR appears more promise in producing the accuracy of correctly classified instances, Naivebayes was proven to be quick at learning. This study has observed that the four records are positively related, and the product's position in online market has also advanced over time. In light of the analysis of the favourable reviews and star ratings, this research study has suggested displaying a potentially successful or disastrous item based on the positive surveys. Finally, the relationship between the quantity of surveys and star ratings are also analyzed.