Criticality and Security Evaluation of Events: Insights for Luxury Hotel Management

Abstract

In this research paper, we present a comprehensive Business Intelligence (BI) framework tailored specifically for luxury hotels to optimize their digital marketing strategies through sentiment analysis of customer reviews. By employing advanced Machine Learning (ML) and Deep Learning (DL) methods, we aim to provide valuable insights into customer sentiments to accurately classify sentiments into positive and negative polarities. We utilize Support Vector Machine (SVM), Random Forests (RF), Naive Bayes classifier (NB), and long short-term memory networks (LSTM) networks to effectively classify insights derived from hotel reviews. To begin, we initially perform data acquisition, followed by the identification of implicit and explicit features, and finally, sentiment classification. To evaluate the performance of our approach, we measure precision, recall, True Positive Rate (TPR), False Positive Rate (FPR), loss, and validation accuracy. Substantially, we conduct a comprehensive comparison of different regularization and optimization methods. Our proposed framework demonstrates exceptional accuracy, particularly on the LSTM network, when compared to SVM, RF, and NB classifiers. This outstanding accuracy establishes the superiority of our approach in effectively categorizing hotel review sentiments.

Index Terms: Sentiment Analysis, security evaluation Review Classification, Luxury hotel Reviews, Smart marketing, Business intelligence, Machine Learning.