Classification of hotel reviews using sentiment analysis and machine learning

Abstract

Social media has become an essential part for people all over the world. It has given a platform for people to share thoughts, emotions, opinions, and ideas, causing a huge deal of data upsurge. Such an amount of data could be analyzed based on sentiment analysis and text classification via construction of an effective machine learning model. The concept gets more insight into it through analysis of the data, which is nearly impossible to conduct manually due to its huge configuration. This research focuses on the user's comments, and reviews about different hotels to predict their sentiment. As for the datasets, comments and reviews of hotels from online sites have been utilized. Moreover, text pre-processing techniques like tokenization, case folding, stopword removal, lemmatization, and duplicate data removal have been applied. TF-IDF and Bag of Words have been applied for word embedding. Furthermore, the effectiveness of supervised machine learning algorithms like, Support Vector Machine, Naïve Bayes, Random Forest, and Logistic Regression was evaluated and from the comparative analysis, it was observed that the Logistic Regression provided the most accuracy ranging from 86 to 89 percent.