Tourism and Hospitality

This study examines the adoption of artificial intelligence (AI) among micro and small hospitality enterprises in Slovenia, a small EU economy where digital transformation remains limited. It explores how organisational characteristics and managers’ attitudes toward AI are related to its adoption and firms’ operating revenues. Data were collected from 286 accommodation and food-and-beverage enterprises through a structured questionnaire completed by managers or owner–managers, complemented by secondary official financial data. Using ordinary least squares regression, the analysis examined associations among organisational characteristics, managerial attitudes, AI use intention and adoption, and financial performance. The results indicate that firm size and structural features alone are not closely linked to digital transformation. AI adoption shows stronger associations with managers’ positive attitudes and with factors such as non-family ownership and smaller firm size. The overall General Attitudes toward AI Scale (GAAIS) score showed no direct relationship with revenue, but two specific items—enthusiasm for AI and recognition of business opportunities—were positively associated with higher revenues. Among AI tools, only smart text editors and CRM systems were statistically associated with revenues, suggesting that better-performing firms are more likely to use simpler, more affordable technologies. The study provides contextual evidence on behavioural and organisational dimensions of AI adoption in resource-constrained hospitality SMEs.

Traditional foods (TFs) represent a key component of regional cultural identity and gastronomic heritage, particularly within the hospitality sector. The growing interest of tourists in authentic, locally sourced and sustainable food underscores the importance of understanding the perceptual and socio-demographic factors that shape their preferences and choices regarding TFs. The aim of this study is to identify and explain the factors that influence tourist attitudes toward dishes prepared with TFs in the hospitality sector, as well as to examine the extent to which socio-demographic characteristics predict tourists’ purchasing decisions. For this purpose, the Tourist Perception and Preferences Model in the Context of Traditional Foods (TPP-TF model) and the Perceptual Factors Scale for Traditional Food Consumption (PFS-TFC) were developed. The research was conducted on a sample of 507 respondents in the A.P. Vojvodina (Republic of Serbia), employing both exploratory and confirmatory factor analyses, which identified the following three key factors: socio-cultural, ecological, and economic. The results of the logistic regression analysisshowed that income level and place of residence significantly influenced the decision to purchase dishes based on traditional foods (TFs). Tourists with higher income levels were substantially more likely to purchase TFs, highlighting the role of economic affordability in shaping consumer choices. Conversely, individuals residing in urban areas showed a significantly lower likelihood of purchasing TFs compared to rural respondents, suggesting that traditional food consumption remains more rooted in rural environments and is closely associated with cultural proximity.

The contemporary digital landscape overwhelms visitors with fragmented and dynamic information, complicating travel planning and often leading to decision paralysis. This paper presents a real-world case study on the design and deployment of an intelligent tourism assistant for Valencia, Spain, built upon a Retrieval-Augmented Generation (RAG) architecture. To address the complexity of integrating static attraction data, live events, and geospatial context, we implemented a multi-agent system orchestrated via the ReAct (Reason + Act) paradigm, comprising specialized Retrieval, Events, and Geospatial Agents. Powered by a large language model, the system unifies heterogeneous data sources—including official tourism repositories and OpenStreetMap—within a single conversational interface. Our contribution centers on practical insights and engineering lessons from developing RAG in an operational urban tourism environment. We outline data preprocessing strategies, such as coreference resolution, to improve contextual consistency and reduce hallucinations. System performance is evaluated using Retrieval Augmented Generation Assessment (RAGAS) metrics, yielding quantitative results that assess both retrieval efficiency and generation quality, with the Mistral Small 3.1 model achieving an Answer Relevancy score of 0.897. Overall, this work highlights both the challenges and advantages of using agent-based RAG to manage urban-scale information complexity, providing guidance for developers aiming to build trustworthy, context-aware AI systems for smart destination management.