,
Research Scholar, Faculty of Management, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India
,
Professor, Faculty of Management, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India
,
Research Scholar, Faculty of Management, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India
Associate Professor, Faculty of Management, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India
Background: The social media engagement has become a crucial ingredient of customer perception in the hospitality industry, especially in budget segments where online reviews make a lot of difference in their decision-making. By understanding the impact of engagement metrics on perceived value and revisit intention, hotel managers can gain insights that can help them improve their customer retention strategies. Methods: The study examine the correlation between social media metrics, perceived value, and revisit intention based on a data set of 10,000 hotel reviews from United States hotels. Several data preprocessing techniques were used to clean the review text, followed by sentiment analysis to extract an overall sentiment score alongside the provided customer ratings. To quantify customer evaluations and future behavioral tendencies, a Perceived Value Index (PVI) and Revisit Intention Score (RIS) were created. For analysis and prediction, correlation analysis, multiple regression, and machine learning models like logistic regression, support vector machine, random forest, and XGBoost were used. Results: The results showed that 63.20% of all the customer reviews were positive and 15.35% of customer reviews were negative. The correlation analysis revealed that there was a strong correlation between perceived value and revisit intention (r = 0.912). The regression results have indicated that the perceived value is the most important predictor of revisit intention (β = 0.537, p < 0.001) reflecting the shared rating and sentiment inputs between the constructed metrics. The best predictive models among the machine learning models were XGBoost with an accuracy of 93.17% and an F1 score of 92.12%. Conclusion: This study illustrates that the online engagement scores have a significant impact on customer-perceived value and revisit intention. The proposed framework is found to be effective in incorporating sentiment analysis along with predictive analytics in budget hotel segments for decision-making in the presence of data and for customer retention strategies.
This is an open access article distributed under the Creative Commons Attribution Non-Commercial License (CC BY-NC) License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
0
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.