Opinion mining using ensemble model for restaurant feedback analysis

The research work introduces a new method for sentiment analysis in the context of restaurant evaluations, emphasizing the optimization of the trade-off between processing time and accuracy. A majority voting classifier is used in our research to evaluate and merge multiple machine learning models, such as Decision Tree, Support Vector Machine, Random Forest, Logistic Regression, K-Nearest Neighbors, Multinomial Naive Bayes, and an Ensemble Method. Thorough preparation of the data, feature extraction, and analysis are all part of the study. Models are then trained and evaluated using performance metrics like accuracy, precision, recall, and F1 score. The main contribution of this work is the integration of models with optimized hyperparameters into an ensemble framework, which greatly improves model performance. Our results show that the ensemble method-the combination of Support Vector Machine, Logistic Regression, and Multinomial Naive Bayes-performs better than both single and multiple models in terms of accuracy and efficiency. Thus, it is determined that the ensemble approach is the best way to perform sentiment analysis on restaurant evaluations, giving restaurant owners valuable business knowledge and important insights for raising customer happiness. By demonstrating the enhanced performance and usefulness of an improved ensemble model in actual food and beverage industry settings, this study contributes to the field of sentiment analysis.