Third wave of hotel website evaluation

an automated machine learning-based approach

Journal Article (2026)
Author(s)

Ceren Şahin (Özyeğin University)

Hanım Kader Şanlıöz-Özgen (Özyeğin University)

Reyhan Aydoğan (Özyeğin University, TU Delft - Electrical Engineering, Mathematics and Computer Science)

Research Group
Interactive Intelligence
DOI related publication
https://doi.org/10.1108/JHTI-01-2026-0050 Final published version
More Info
expand_more
Publication Year
2026
Language
English
Research Group
Interactive Intelligence
Journal title
Journal of Hospitality and Tourism Insights
Pages (from-to)
1-28
Page Views
22

Abstract

Purpose – This interdisciplinary research combining the fields of tourism and computer science aims to develop a framework (HotelWebComp) as a Web application for the automated analysis of hotel websites using machine learning (ML) techniques. Design/methodology/approach – The study outlines the methodology utilizing Web data via Web Crawling and Scraping and employs various AI tools including ontology reasoning and ML to propose a framework for assessing hotel websites and identifying key features for improvement. The Web application was tested using a sample of 50 hotel websites. Findings – A Web-based automated assessment application (HotelWebComp), which calculates a competence score for a given hotel website has been developed to help hotels enhance their direct online booking capacities. Practical implications – The research can be situated within a broad understanding of the UN sustainable development goals, responding in particular to goals 9 and 11 to propose an innovative framework to help increase the profitability of small, medium and independent hotels in particular, which can in turn lead to wider economic benefits to the destination communities and generating increases of income and a more diverse and sustainable tourist industry. Originality/value – The study demonstrates how the application of ML tools when assessing hotel websites can drive online competitive advantage within the hotel industry. The major impact of the study is to propose an ML-based approach supporting the automated method to assess hotel websites combining technical and marketing aspects to drive hotels' competitiveness.