article · Procedia Computer Science
Smart tourism destinations increasingly rely on mobile applications powered by artificial intelligence and natural language processing to enhance visitor experiences. While chatbots provide a useful conversational interface for these applications, building them remains technically challenging. Developers face hurdles such as high natural language processing service costs and the need for specialised expertise across artificial intelligence and software engineering. Existing commercial development frameworks often require complex configuration and lack domain-tailored design tools. To address these issues, combining software factories with domain-specific languages offers a structured path forward. Software factories automate the engineering workflow to accelerate development and maintain design consistency. Concurrently, a model-driven domain-specific language provides high-level abstractions specifically tailored to the operational demands of smart tourism mobile applications, making the design and implementation of customised conversational agents more accessible and efficient.
Smart tourism destinations need responsive digital tools to support visitors, but building customised conversational assistants can be expensive and technically demanding. Introducing automated development methods and specialised modelling languages simplifies this process. This lowers technical barriers for tourism organisations, making it easier to deploy consistent, tailored chatbots that assist travellers before, during, and after their visits.
This work could assist software engineers and destination management organisations seeking to create chatbots for smart tourism applications. By using automated software factories and domain-specific languages, teams could cut development costs and reduce reliance on deep artificial intelligence expertise. The research presents a model-driven design approach, which places it at an early, conceptual or design stage of development, with real-world implementation and commercial readiness still requiring further practical validation.
AI-generated from the published abstract. Always read the original work before citing.
Today, the tourism industry is significantly impacted by mobile applications leveraging Artificial Intelligence (AI) and Natural Language Processing (NLP) to enhance tourists' experiences before, during, and after their visits. This technological convergence has given rise to Smart Tourism Destinations (STDs). However, efficiently integrating these functionalities into mobile apps poses a major challenge, leading to the emergence of chatbots. Companies like IBM, Google, Microsoft, and Amazon offer tools such as Watson, Bot Framework, Dialogflow, and Amazon Lex for their development. Nevertheless, creating chatbots remains intricate, demanding expertise in software development and AI, along with associated costs related to NLP service providers. Additionally, employing an appropriate modeling language is crucial for designing a chatbot. At this juncture, the concepts of software factories and Domain-Specific Languages (DSLs) become indispensable. These innovative approaches provide solutions for addressing these complex challenges. Software factories automate the development process, expediting chatbot creation while ensuring consistency. Simultaneously, DSLs furnish tools for accurately modeling and articulating the specific requirements of smart tourism, simplifying the development of tailor-made chatbots suited to this domain. This article introduces a model-driven approach for a DSL aimed at offering an abstract, high-level representation of the various aspects of chatbots within the context of an intelligent tourism mobile application.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.procs.2023.12.203
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
