Optimizing Sentiment Analysis of Hotel Reviews Using PCA and Machine Learning for Tourism Business Decision Support

Aug 5, 2026

Sentiment analysis of hotel reviews supports tourism business decision-making by revealing customer satisfaction and service-quality signals from online feedback. The study addresses review-data challenges such as high dimensionality and unstructured text by applying Principal Component Analysis (PCA) for dimensionality reduction and feature selection, then training machine learning classifiers for sentiment categories. A full pipeline covers preprocessing, PCA-based feature refinement, model training, and performance evaluation. Results indicate improved accuracy and computational efficiency, with Voting reaching 95.29% accuracy and 97.50% F-score, and BiLSTM-FNN achieving 99.95% recall, enabling better management actions, customer experience enhancement, and marketing strategy targeting.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

Challenges in Hotel Review Sentiment Analysis

Traditional Models and Limitations

PCA for Dimensionality Reduction

Machine Learning Models for Sentiment Classification

Prior Studies and Comparative Approaches

Optimizing Sentiment Analysis of Hotel Reviews Using PCA and Machine Learning for Tourism Business Decision Support P T Prasetyaningrum*1, N Ibrahim2, O Suria3 1,3Information Systems Study Program, Faculty of Information Technology, Universitas Mercu Buana Yogyakarta 2Fakultas Komputasi dan Meta-Teknologi, University Pendidikan Sultan Idris, Tanjong Malim, Perak, Malaysia [E-mail:](E-mail: putri@mercubuana-yogya.ac.id1)[ ](E-mail: putri@mercubuana-yogya.ac.id1)[putri@mercubuana-yogya.ac.id](E-mail: putri@mercubuana-yogya.ac.id1)[1](E-mail: putri@mercubuana-yogya.ac.id1), [shahila@meta.upsi.edu.my](shahila@meta.upsi.edu.my2)[2](shahila@meta.upsi.edu.my2), [ozzi@mercubuana-yogya.ac.id](ozzi@mercubuana-yogya.ac.id3)[3](ozzi@mercubuana-yogya.ac.id3) Abstract. Sentiment analysis of hotel reviews provides valuable insights for improving customer satisfaction and service quality in the tourism industry. However, the high dimensionality and unstructured nature of review data pose challenges in extracting meaningful insights. This study optimizes sentiment analysis by applying Principal Component Analysis (PCA) for dimensionality reduction and utilizing machine learning models for classification. The proposed approach involves data preprocessing, feature selection using PCA, model training, and performance evaluation. Experimental results show that PCA enhances classification accuracy and computational efficiency by eliminating redundant features, improving sentiment prediction. The comparative analysis demonstrates that the Voting classifier achieves the highest accuracy (95.29%) and F-score (97.50%), while the BiLSTM-FNN model attains the highest recall (99.95%) . These findings highlight the potential of PCA-based sentiment analysis in supporting data-driven decision-making for hotel management, enabling enhanced service quality, improved customer experience, and effective marketing strategies. Keywords: Sentiment analysis; Hotel reviews; PCA; Machine learning; Voting; BiLSTM-FNN. 1. Introduction The rapid development of digital technology and the internet's widespread use have transformed how customers express their opinions and experiences, particularly in the hospitality and tourism industry [1] . Online hotel reviews have become a critical source of information for potential customers in making travel decisions and for hotel management in evaluating service quality [2], [3] [4], [5] . However, customer reviews’ large volume and unstructured nature present challenges in extracting valuable insights effectively [6], [7] . Sentiment analysis, a method within natural language processing (NLP), enables the classification of customer opinions into positive, negative, or neutral categories, providing a data-driven approach to understanding customer satisfaction [8], [9] . Despite the growing application of sentiment analysis in various industries, optimizing its accuracy and efficiency remains challenging [10], [11], [12], [13], [14], [15] . Traditional sentiment analysis models often struggle with high-dimensional text data, leading to increased computational complexity and reduced classification performance [16], [17], [18] . Principal Component Analysis (PCA) has been widely utilized to address this issue by reducing dimensionality while preserving essential features [19], [20] . Machine Learning models enhance sentiment classification by improving predictive accuracy and generalizability across different datasets [21], [22] . Sentiment analysis can be performed using various classification techniques, with Naïve Bayes (NB), Support Vector Machine (SVM), and k-nearest Neighbor (k-NN) being among the most commonly used methods. Several studies have explored these classification approaches. For instance, research conducted by Sanjay et al. employed NB and SVM algorithms to analyze sentiment in Amazon product reviews[23] . Wasim and Hassan conducted a study using the Support Vector Machine (SVM) algorithm to cla

FAQs

Why is sentiment analysis of hotel reviews important for tourism businesses?

It converts customer feedback into positive, negative, and neutral signals that help potential customers and hotel managers assess service quality and satisfaction.

How does PCA improve the proposed sentiment analysis approach?

PCA reduces dimensionality by removing redundant features, which improves classification accuracy and computational efficiency while preserving essential information.

Which models showed the best performance in the study?

The Voting classifier achieved the highest accuracy (95.29%) and F-score (97.50%), while the BiLSTM-FNN model achieved the highest recall (99.95%).

Aug 5, 2026

Upload by Valentina