Intelligent Smart Tourism Education: AI-based Learning for Cultural Tourism Experiments Michele Angelaccio1,*,†, Michele Fasolo,1,† and Lucia Zappitelli1,† 1Dipartimento Ingegneria dell’Impresa (DII), University of Rome “Tor Vergata”, via del Politecnico 1, Rome, 00100, Italy Abstract Self-learning and active learning are becoming key focal points in the digital era, where the demand for online learning is growing. This is particularly important for the education of smart tourism guides within the context of cultural tourism. In this paper, we present some experiences obtained within the context of the Digital Tourism Course at the University of Rome Tor Vergata over the past two years. The focus is on enhancing self-learning skills through the use of AI generative techniques and its role in digitalizing cultural tourism. We also provide comparisons and discussions on the reported advantages. Keywords Smart cultural tourism, inclusive learning, self-learning, AI, generative models1 1. Introduction enhancing learning experiences. One of the notable applications of AI in education is AI-assisted learning, The integration of artificial intelligence (AI) in which leverages machine learning algorithms and education, particularly in the field of digital tourism, is natural language processing techniques to a growing area of interest. Xing (2022) and Cesta personalize and optimize the learning process for (2020) both emphasize the potential of AI in individual students. This introduction aims to provide personalizing learning experiences, with Xing an overview of AI-assisted learning, drawing insights focusing on the design of a tourism teaching system from a survey of relevant literature. and Cesta on the use of intelligent tools for cultural AI-assisted learning encompasses a variety of heritage visits. Ferràs (2020) further explores the techniques and technologies aimed at tailoring application of AI in tourism, highlighting its role in educational content, delivery, and assessment to meet creating customized experiences. Morellato (2014) the diverse needs and preferences of learners. As adds a new perspective, proposing an experiential highlighted by [4], AI systems can analyze vast approach to developing digital competence in tourism amounts of educational data, including student education, which could be enhanced by AI-driven performance, learning styles, and knowledge gaps, to personalization and active learning. These studies generate personalized learning pathways and collectively underscore the potential of AI in recommendations. These systems can adaptively transforming the learning experience in digital adjust the difficulty level of learning materials, tourism, from personalized teaching systems to the provide real-time feedback, and offer additional creation of tailored tourist experiences. resources or exercises based on individual learning In recent years, the integration of artificial progress and proficiency. intelligence (AI) into education has been rapidly Moreover, AI-powered tutoring systems have advancing, offering promising opportunities for shown great potential in providing personalized Ital-IA 2024: 4th National Conference on Artificial Intelligence, fasolo@ uniroma2.it (M. Fasolo); lucia.zappitelli@gmail.it (L. organized by CINI, May 29-30, 2024, Naples, Italy Zappitelli) ∗ Corresponding author. † These authors contributed equally. © 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). michele.angelaccio@uniroma2.it (M. Angelaccio); CEUR ceur-ws.org Workshop ISSN 1613-0073 Proceedings support and guidance to students. For instance, provide personalized recommendations for intelligent tutoring systems (ITS) can simulate one- activities that match the learner's current level of on-one interactions with students, offering immediate knowledge, ensuring that they are appropriately feedback, explanations, and hints tailored to their challenged without feeling overwhelmed or specific learning needs [2]. Through the use of natural bored. By adapting to the learner's evolving language understanding and dialogue generation abilities, adaptive learning systems promote techniques, chatbot-based tutoring systems can continuous improvement and engagement in self- engage in conversational interactions with learners, learning activities. answering questions, clarifying concepts, and fostering a supportive learning environment [5]. • Intelligent Tutoring Systems (ITS) ITS leverage AI techniques to simulate one- Furthermore, AI-assisted learning extends beyond on-one tutoring interactions, providing individualized tutoring to collaborative and social personalized guidance, feedback, and learning experiences. Social recommender systems support to learners. Through natural can leverage AI algorithms to analyze learners' social language processing and machine learning interactions, preferences, and interests, facilitating algorithms, ITS can understand the learner's the discovery of relevant learning resources and questions, misconceptions, and learning fostering peer-to-peer knowledge sharing [6]. Virtual goals, offering targeted explanations, hints, collaborative environments powered by AI can enable and examples to facilitate self-directed students to engage in collaborative problem-solving, learning. By providing immediate and project-based learning, and group discussions, with tailored assistance, ITS empower learners to intelligent agents providing guidance, coordination, navigate complex concepts and topics and feedback throughout the collaborative process independently. [3]. In this paper we outline some experiences • Recommendation Systems obtained in the context of Digital Tourism Course at AI-driven recommendation systems analyze the University of Rome Tor Vergata in the last 2 years. learners' preferences, past interactions, and The focus is on improving self-learning skills with the learning objectives to suggest relevant use of AI generative and its role in the context of resources, courses, and activities for self- cultural tourism digitalization motivated by several directed learning. These systems can reasons as described in [1] in which the importance of recommend educational materials, such as academic role has been outlined. articles, videos, tutorials, and online courses, that align with the learner's interests and 2. Impact of AI in Providing Self- goals, thereby facilitating serendipitous discovery and exploration of new topics. By Learning Activities curating personalized learning pathways, The impact of AI in providing self-learning activities is recommendation systems empower profound and multifaceted. Here are several key ways learners to take ownership of their learning in which AI influences self-learning: journey and pursue areas of interest autonomously. • Personalized Learning Paths • Natural Language Processing (NLP) AI can analyze vast amounts of data about a NLP technologies enable interactive and learner's preferences, strengths, weaknesses, and conversational interfaces for self-learning learning styles to tailor educational content and activities, such as chatbots and virtual activities to their individual needs. By assistants. Learners can engage in dialogue understanding the learner's pace and level of with AI-powered agents to ask questions, understanding, AI algorithms can suggest seek explanations, and receive feedback in appropriate resources, exercises, and challenges, natural language. By fostering interactive thereby enabling self-directed learning that is and responsive learning experiences, NLP- customized to each learner. driven systems support self-directed • Adaptive Learning Systems inquiry, reflection, and problem-solving, AI-powered adaptive learning systems enhancing learners' autonomy and dynamically adjust the difficulty and pace of confidence in their ability to learn learning activities based on the learner's independently. performance and progress. These systems can Overall, AI plays a transformative role in enabling and destinations, while those interested in immersive enhancing self-learning activities by providing experiences may be directed to resources on virtual personalized guidance, adaptive support, curated reality technologies. resources, interactive interfaces, and actionable feedback. By leveraging the capabilities of AI 3.1.2. Chatbot Assistance technologies, learners can engage in self-directed To facilitate seamless navigation and access to learning that is tailored to their individual needs, resources, the platform features a chatbot interface preferences, and aspirations, thereby empowering that serves as a virtual assistant. Learners can interact them to become lifelong learners mastering new with the chatbot using natural language queries to skills, acquiring knowledge, and achieving their request specific information or resources. For educational goals autonomously. instance, a learner interested in learning about the use of augmented reality in cultural tourism may type "AR 3. Case Description: Self-Learning in applications" into the chatbot interface. The chatbot Digitalization of Cultural Tourism then retrieves relevant PDF documents, articles, and videos from the platform's database and presents Digitalization of cultural routes is a key point used in them to the learner for exploration. the education of new generation of tour operators and smart guides. Self-Learning AI powered activities 3.1.3. Accessing PDF Resources provide in this case a promising means to guarantee a flexible and dynamic learning process suitable in the One of the key functionalities of the chatbot is its new tourism era and in particular cultural tourism ability to provide access to PDF resources on demand. case. To demonstrate the applicability of AI based Learners can request PDF documents on specific education in cultural tourism, we consider three topics by simply typing keywords or phrases related examples used in the Rome Tor Vergata University. to their interests. For example, a learner curious about the impact of digitalization on cultural heritage 3.1. Self-learning Platform for Cultural preservation may type "heritage preservation" into the chatbot interface. The chatbot then searches the Travel Blog Design platform's repository for PDF documents, reports, or A first Example of Digital Tourism learning activity research papers related to the topic and presents is the digitalization of cultural routes emerging from them as downloadable resources. the need to explore archeo sites and cultural heritage assets in a huge number of ways. As example of self- 3.1.4. Interactive Learning Activities learning platform, we discuss the case of cultural In addition to accessing static resources, learners travel blog designed for walking routes and denoted can engage in interactive learning activities to deepen as cultural travel blog in which information is their understanding of digitalization in cultural designed to offer comprehensive resources and tourism. These activities may include quizzes, interactive activities focused on the digitalization of simulations, virtual tours, and collaborative projects, cultural tourism. Learners have access to a variety of allowing learners to apply theoretical concepts in multimedia content, including articles, videos, case real-world scenarios and gain hands-on experience in studies, and tutorials, covering topics such as digital digital cultural heritage management. marketing strategies for cultural attractions, virtual reality experiences in heritage sites, and augmented 3.1.5. Progress Tracking and Feedback reality applications for guided tours. Throughout their learning journey, learners can 3.1.1. Personalized Learning Paths track their progress and performance using built-in analytics and assessment tools. AI algorithms analyze Upon accessing the platform, learners are learner interactions, quiz scores, and completion rates prompted to create a profile where they can specify to provide personalized feedback and their interests, goals, and prior knowledge in the field recommendations for further learning. Learners of cultural tourism. AI algorithms analyze this receive insights into their strengths and areas for information to generate personalized learning paths improvement, empowering them to adapt their tailored to each learner's preferences and learning learning strategies and goals accordingly. objectives. For example, learners interested in digital marketing may receive recommendations for articles and tutorials on social media advertising for cultural The self-learning platform for digitalization of BEFORE Master cultural tourism offers a flexible and engaging Marketing, Communication educational experience, enabling individuals to TRAVEL Skills Destination Designer acquire knowledge and skills at their own pace and Planning Narrative convenience. By harnessing the capabilities of AI CULTURAL Destination LOCAL knowledge and Technical, Practical Skills Experience Skills Tour TRAVEL Skills technologies and interactive resources, the platform Local Operator People Cultural Focus Expert empowers learners to explore the intersection of Collaborate culture, technology, and tourism and become Travel informed advocates for sustainable and inclusive Guide digital practices in cultural heritage preservation and promotion. Destination AFTER Master Designer LESS Planning Destination AI Travel 3.2. Self-learning activities for local Smart Online learning chatBot AI powered skills Self learning + engangement Trained + economic benefits Local Cultural Operators People Cultural Expert AI Travel Guide As another example of the application of a self- Smart Tour Operator Skills Master Organization AI Expert learning platform, we highlight the case of Archeo AI Models Tutorial, implemented within the context of the AI generated Packet ERASMUS+ project ADHOC. The platform's role is to AI Builder enhance accessibility for users with disabilities. In this context, the platform has been equipped with a Figure 1: AI-Power Master of Local Cultural Guides dynamic generative script for the text-to-speech Overview function, allowing it to be seamlessly integrated into the original archaeological guide. Obviously, this 3.3. Accessing a PDF Book on Cultural Routes generation can be put in the form of NLP by taking in Rome advantage from a chatbot interacting with PDF resources. This approach showcases how AI In this latter example, we aim to highlight an generative interaction with PDF resources can serve instance of an AI-powered application utilizing as a viable solution for self-learning activities aimed at advanced AI-assisted self-cultural guidance. The educating cultural guides. This is particularly valuable learner communicates their interest in cultural routes in contexts where there is a need to extend cultural in a densely populated cultural destination such as tourism learning to students with disabilities, as part Rome through a natural language query to the of an inclusive learning program. For instance, in the chatbot. The chatbot recognizes the learner's request case of translating cultural content into LIS (Italian and responds by asking a PDF book. Sign Language), the learning program is tailored for Exploring historical cities like Rome can now students who are already proficient in using LIS. benefit from a variety of digital tools (applications, Figure 1 illustrates the impact of AI-powered augmented reality, chatbots, and interactive maps) learning methodologies on the education of local that facilitate immediate access to the dense and cultural guides. The diagram depicts the gains and hyper-dimensional fabric of data, stories, and paths benefits that could be achieved through the Master's related to the cultural components of the urban program (see also 8]). landscape. Particularly, the integration of intelligent chatbots and interactive maps, programmed with extensive databases of information, represents an innovative breakthrough in the cultural tourism sector capable of offering users immediate answers to specific questions, recommendations tailored to their interests and needs, as well as real-time updates on events in the explored context, significantly enriching the personal experience and making it unique and rich. In this regard, a case study aimed at optimizing the touristic exploration of Rome is proposed, based on the innovative integration of an advanced chatbot, built on generative artificial intelligence technologies, and Leaflet, an open-source platform for creating interactive maps. This synergy specifically aims to learning experiences through its technological offer a highly personalized tourist experience, within features (intelligent tutoring systems and chatbots) the scope of themes chosen by the user, encompassing that cater to the needs for personalization and a wide spectrum of cultural components of the urban adaptability. This work particularly investigates the landscape, from artistic and historical to importance and impact of AI, with a special reference enogastronomic elements. This system, named to AI-assisted learning in the field of cultural tourism. GuidaTuristicaAI (or AI-CH-Tour-Map), includes in its There are several ways in which AI can be enabled for descriptions information drawn from a vast corpus of better personalization and improvement of the documents, ranging from books by illustrious visitors, educational experience, namely customizing learning literary works, and musical compositions, to paths, advanced tutoring systems, recommendation enogastronomic guides about Rome over the mechanisms, and the use of natural language centuries. Upon interacting with GuidaTuristicaAI, the processing to enhance interaction and support for user is invited to select one or more themes of interest students. The research has specifically focused on the to further personalize their exploration of the city. If use of self-learning platforms in the production of the choice falls, for example, on literary works about blogs dedicated to cultural travel, emphasizing the Rome as a thematic filter, the chatbot searches its PDF importance of digitalizing cultural routes. Particular document database to select those including literary attention was given to specific use cases implemented references to Rome, extracted from works by famous at the University of Rome "Tor Vergata", highlighting authors who have described the city in their visits or how AI solutions can enable self-learning and narrative and poetic works. In the case study, it is accessibility for users with disabilities, aiming to imagined that an art history student plans a visit to ensure a better experience in their training for future Rome following the footsteps of Giuseppe Vasi. The professionals. AI can help and enhance a series of chatbot suggests a series of publications. For example, activities conducted in self-learning through personal they can download the PDF of one of the volumes from guidance, adaptive support, and interactive interfaces the open archive.org site or another to resources. It allows students to follow a self- source:( https://ia801006.us.archive.org/7/items/te regulated learning path that, according to their needs, sorosacroevene02vasi/tesorosacroevene02vasi.pdf ) preferences, and personal goals, enables approaches . Using the web application, the user receives a to lifelong learning, which can empower them to personalized itinerary with the sites described by acquire new skills and knowledge entirely Vasi. The generated interactive map allows him to autonomously. Such flexible and interactive self- easily navigate from one place to another, while the learning modalities can be effectively extended into chatbot provides cultural and historical insights. The digital tourism, facilitating experiences by any user in Leaflet mapping platform plays a crucial role in the consuming cultural landscapes in a more accessible implementation of this thematic customization. The and engaging way. dynamism of the real-time interaction between the user and GuidaTuristicaAI can indeed be enriched with specific points of interest identified on the map related to other themes selected by the user, allowing References them to discover the city through different [1] Amato, Flora, et al. "Ai-powered learning: interpretative and perceptual lenses. For example, in Personalizing education for each student." 3rd accord to the literary theme, markers can be added to CINI National Conference on Artificial places mentioned in novels or poems, with short Intelligence (ITAL-IA 2023), in Pisa, Italy. 2023. excerpts or quotes visible by clicking on the respective [2] J. R. Anderson et al. “Cognitive tutors: Lessons markers, emotionally connecting them to the places learned”, Journal of the through the words of authors who have immortalized Learning Sciences (1985), pp. 167–207. them in their works. Moreover, information can be doi:10.1207/s15327809jls0402_2. provided on dining venues and typical Roman dishes [3] T. De Jong and A. W. Lazonder. “Designing and wines that can be paired with them. Virtual Collaborative Learning Environments”. In: Learning, Design, and Technology: An 4. Conclusions International Compendium of Theory, Research, From the outset and in the coming years, AI Practice, and Policy. Ed. by M. Spector, B. B. promises to play a decisive innovative role in the field Lockee, and M. D. Childress. Springer, 2016, pp. of educational pathways, transforming and enhancing 1–23. doi: 10.1007/978-3-319-17727-4_179-1 [4] A. Smith. “AI in Education: Promises and Transactions on Emerging Topics in Computing Pitfalls”. In: Journal of Edu- 5.2(2017), pp.208–219. cational Technology 45.3 (2020), pp. 321–335. [7] https://projectadhoc.files.wordpress.com/202 doi:10.1080/0000000X.2020.1234567. 2/12/ad-hoc-italian.pdf [5] X. Wang et al. “Designing chatbots for tutoring: A [8] Angelaccio Michele, Zappitelli Lucia, “Active collaborative approach”. In: International Learning in Teaching Digital Tourism: Journal of Artificial Intelligence in Education preliminary results through Online Travel 29.4 (2019), pp. 533–574. doi: 10.1007/s40593- Business Simulation.” In: eLmL 2023, The 019-00192-y. Fifteenth International Conference on Mobile, [6] J. Yu et al. “Social recommendation for e-learning Hybrid, and On-line Learning. IARIA, 2023. p. 1- systems: A survey of the state-of-the-art and 4. future research directions”. In: IEEE