Recent Papers

In recent years, the growth of online review platforms has provided consumers with vast amounts of user-generated feedback. For businesses, especially in the food and hospitality industry, this feedback holds critical value for understanding customer satisfaction and improving services. However, manually analyzing these reviews is inefficient due to their volume. This paper presents a machine learning-based approach to automatically classify the sentiment of restaurant reviews into positive, negative, or neutral categories. By employing natural language processing (NLP) techniques, including tokenization, text normalization, and feature extraction, we create a robust dataset for sentiment analysis. Various classification models such as Support Vector Machines (SVM), Logistic Regression, and Deep Learning architectures (e.g., LSTM and BERT) are explored and evaluated based on their accuracy, precision, and recall. The results demonstrate that deep learning models, especially those utilizing contextual embeddings like BERT, outperform traditional models in accurately capturing the sentiment. This automated system provides restaurant owners and stakeholders with valuable insights for decision-making and improving customer satisfaction.

Copyright © 2024 Shrushti makne, shraddha gawade, Aarti shirsat, Apeksha Pawar. This is an open access article distributed under the Creative Commons Attribution License.