Context in AI-driven hospitality personalization
| Context | Focused | Document |
|---|---|---|
| Post-pandemic proximity tourism | Short trips, weekend getaways and day trips, where the destination is close to home and offers nature-based recreation | Lin et al. (2025) |
| Hong Kong tourism competitiveness across four periods (pre-pandemic, pandemic, early post-pandemic, new normal) | Focus on experience-driven competitiveness, not static resource/economic factors, especially when visiting Hong Kong | Chen et al. (2025) |
| Captures discourse during rapid metaverse development, particularly after the COVID-19 pandemic shifted travel and tourism habits | Public beliefs about metaverse tourism, how people perceive virtual tourism, its opportunities, drawbacks and future potential | Mahmoud et al. (2024) |
| Hospitality setting in a 222-room hotel in Thailand, focusing on chambermaid scheduling and on-demand guest service. (case study in Ubon Ratchathani Province) | Focus on real-time chambermaid scheduling and guest service personalization. This real-time environment has high occupancy rates (75%), multiple room types (standard, deluxe, suite) and evolving guest expectations | Pitakaso et al. (2025) |
| 10 of the most popular African destinations, including Cape Town, Marrakesh, Nairobi and Arusha | Particular attention is given to reviews that contain emotional reflection, showing satisfaction/dissatisfaction as a post-consumption evaluation process | Mensah et al. (2025) |
| Assessing the alignment between technological capabilities and task characteristics influences outcomes in online hotel review responses | This paper focuses on how response helpfulness varies with AI configuration (temperature) and review valence (positive vs negative) | Zhang et al. (2025) |
| Online food service platforms in China (Meituan) | Consumers’ perceptions of price fairness using configurational analysis | Tan et al. (2025) |
| Customer evaluation of AI-themed hotels across different categories (luxury, budget chain and budget independent) using online review data | Explores how configurations of technology-related (attractive) and basic (must-be) qualities impact positive guest evaluations using topic modeling and fsQCA | Yi et al. (2024) |
| Growing use of digital reviews in tourism and low-resource feedback analysis tools is needed | Using zero-shot LLMs for sentiment analysis and keyword extraction | Guidotti et al. (2025) |
| Using TripAdvisor reviews to understand why people travel | Automatically classify the purpose of a trip (e.g. business, family) from a single review using machine learning and text analysis | Félix et al. (2025) |
| Addressing challenges in analyzing tourism user-generated content using AI | Benchmarking LDA, BERT and GPT-4 for Effective Topic Modeling in Tourism Research | Kirilenko and Stepchenkova (2025) |
| Consumer decision-making in hotel bookings on whether to include breakfast | How constant breakfast surcharges and varying room prices influence breakfast demand through salience-driven attention to price vs value | Anguera-Torrell and Nicolau (2025) |
| Chain hotels in Western Thailand’s coastal tourism areas are using AI-enabled services | Examining how AI service features influence customer satisfaction and loyalty | Chotisarn and Phuthong (2025) |
| Visitor satisfaction in London using digital sentiment (“smiley”) analysis of Airbnb and hotel reviews | How spatial factors (like proximity to parks and transport) influence tourist appreciation, especially during COVID-19 | Kourtit et al. (2025) |
| Leveraging digital analytics and customer-generated content to enhance brand equity assessment in the evolving hospitality industry | Investigating hotel brand equity through text mining of customer reviews and customer journey mapping, using Amari Phuket as a case | Piriyakul et al. (2024) |
| Develops a domain-specific sentiment dictionary based on discrete emotion theory | Analyzing diverse visitor emotions in the hospitality and tourism sector, especially from Chinese online reviews | Yu et al. (2024) |
| Investigate the various dimensions of robot restaurant experiences | Extracted from online reviews, influence customers’ actual recommendation behavior using text mining and sentiment analysis | Li et al. (2024) |
| Shaping tourist destination perceptions through User-Generated Visual Content on Instagram | Focuses on how photo content and sender type affect engagement, using AI to analyze Instagram posts | Blanco-Moreno et al. (2024) |
| Explores the reuse potential of fortified cultural heritage in Venice by applying fuzzy expert systems and self-organizing maps | Proposes a hybrid decision-support model using fuzzy logic and machine learning to assess reuse potential in the Venice Lagoon | Camatti et al. (2025) |
| Explores how tourism activity relates to social, economic and environmental well-being across Italian provinces | Investigates the spatial and statistical correlation between tourism indicators and well-being metrics using machine learning and XAI techniques | Firza et al. (2024) |
| To explore how machine learning based analysis of hotel reviews can guide sustainable and customer-centric practices aligned with the sustainable development goals | Specially focused on online reviews from global platforms. Examples include hotels in the USA, Thailand, Denmark, Bhutan, Japan and the Maldives | Gupta and Jaiswal (2024) |
| Context | Focused | Document |
|---|---|---|
| Post-pandemic proximity tourism | Short trips, weekend getaways and day trips, where the destination is close to home and offers nature-based recreation | |
| Hong Kong tourism competitiveness across four periods (pre-pandemic, pandemic, early post-pandemic, new normal) | Focus on experience-driven competitiveness, not static resource/economic factors, especially when visiting Hong Kong | |
| Captures discourse during rapid metaverse development, particularly after the COVID-19 pandemic shifted travel and tourism habits | Public beliefs about metaverse tourism, how people perceive virtual tourism, its opportunities, drawbacks and future potential | |
| Hospitality setting in a 222-room hotel in Thailand, focusing on chambermaid scheduling and on-demand guest service. (case study in Ubon Ratchathani Province) | Focus on real-time chambermaid scheduling and guest service personalization. This real-time environment has high occupancy rates (75%), multiple room types (standard, deluxe, suite) and evolving guest expectations | |
| 10 of the most popular African destinations, including Cape Town, Marrakesh, Nairobi and Arusha | Particular attention is given to reviews that contain emotional reflection, showing satisfaction/dissatisfaction as a post-consumption evaluation process | |
| Assessing the alignment between technological capabilities and task characteristics influences outcomes in online hotel review responses | This paper focuses on how response helpfulness varies with | |
| Online food service platforms in China (Meituan) | Consumers’ perceptions of price fairness using configurational analysis | |
| Customer evaluation of AI-themed hotels across different categories (luxury, budget chain and budget independent) using online review data | Explores how configurations of technology-related (attractive) and basic (must-be) qualities impact positive guest evaluations using topic modeling and fsQCA | |
| Growing use of digital reviews in tourism and low-resource feedback analysis tools is needed | Using zero-shot LLMs for sentiment analysis and keyword extraction | |
| Using TripAdvisor reviews to understand why people travel | Automatically classify the purpose of a trip (e.g. business, family) from a single review using machine learning and text analysis | |
| Addressing challenges in analyzing tourism user-generated content using | Benchmarking LDA, | |
| Consumer decision-making in hotel bookings on whether to include breakfast | How constant breakfast surcharges and varying room prices influence breakfast demand through salience-driven attention to price vs value | |
| Chain hotels in Western Thailand’s coastal tourism areas are using AI-enabled services | Examining how | |
| Visitor satisfaction in London using digital sentiment (“smiley”) analysis of Airbnb and hotel reviews | How spatial factors (like proximity to parks and transport) influence tourist appreciation, especially during COVID-19 | |
| Leveraging digital analytics and customer-generated content to enhance brand equity assessment in the evolving hospitality industry | Investigating hotel brand equity through text mining of customer reviews and customer journey mapping, using Amari Phuket as a case | |
| Develops a domain-specific sentiment dictionary based on discrete emotion theory | Analyzing diverse visitor emotions in the hospitality and tourism sector, especially from Chinese online reviews | |
| Investigate the various dimensions of robot restaurant experiences | Extracted from online reviews, influence customers’ actual recommendation behavior using text mining and sentiment analysis | |
| Shaping tourist destination perceptions through User-Generated Visual Content on Instagram | Focuses on how photo content and sender type affect engagement, using | |
| Explores the reuse potential of fortified cultural heritage in Venice by applying fuzzy expert systems and self-organizing maps | Proposes a hybrid decision-support model using fuzzy logic and machine learning to assess reuse potential in the Venice Lagoon | |
| Explores how tourism activity relates to social, economic and environmental well-being across Italian provinces | Investigates the spatial and statistical correlation between tourism indicators and well-being metrics using machine learning and | |
| To explore how machine learning based analysis of hotel reviews can guide sustainable and customer-centric practices aligned with the sustainable development goals | Specially focused on online reviews from global platforms. Examples include hotels in the USA, Thailand, Denmark, Bhutan, Japan and the Maldives |
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.