The main purpose of this chapter is to understand how artificial intelligence (AI) has evolved in the academic literature on visitors' spatiotemporal behaviour (STB), identifying the key thematic areas that have drawn most research interest to help academics and professionals to gain a better understanding of AI usage on this topic. The literature review was based on a search of scientific documents available on the Scopus platform concerning the use of AI on visitors' STB studies. On a first stage the number of documents published per year and the identification of the most representative journals and authors are presented and discussed. On second stage, a content analysis was conducted, and bibliometric method such as, co-occurrence analysis, was used. The most productive and cited authors were identified and although the number of articles published is not very high, reveal some interest of researchers on this issue, particularly during 2023. The most important key thematic areas and some implications for future research were also identified and discussed.
TopIntroduction
The significant increase in the number of documents on the spatiotemporal behaviour of tourists (SBT) available on the Scopus platform leads us to conclude that the interest of tourism researchers in this topic has been growing over the last few decades (Shoval & Ahas, 2016), with new technologies being used to accurately track movements, such as Global Position System (GPS) devices (Shoval et al., 2020), smartphone GPS applications (M. R. Martins et al., 2022), Bluetooth (Versichele et al., 2012), Passive mobile positioning data (Ahas et al., 2008) or the user-generated content (UGC) of some social networks (Chua et al., 2016; Hausmann et al., 2018; Kádár & Gede, 2022) where users share geotagged photographs or georeferenced walking trails in natural and/or urban environments. All these modern methods and techniques used to collect information on the movements made by tourists are more efficient and accurate and reduce the responsibility of the individuals, as they are not reliant on their enthusiasm and memory. GPS technology is also mature and easy to use (Xia, 2007), particularly through the Geographic Information Systems (GIS) software.
However, the large amount of data collected results in terabytes of information available for knowledge extraction and decision-making (Jayawardena et al., 2013) and “require the development of more algorithms to enable automatic scripts to analyze the data in a fast and practical way” (Shoval & Ahas, 2016, p.16), as well as researchers, specialised in different areas of knowledge such as computer science, programming, geography, among others. Therefore, it will be necessary to use advanced data analysis methods and techniques and develop machine learning technologies and deep learning algorithms to interpret the data accurately and efficiently apply the outcomes (West et al., 2018).
Generally speaking, AI can be defined as the science of making machines that can think like humans, processing large amounts of data in order to recognize patterns, make decisions, and judge like humans (Pattam, 2021), i.e., is a technology that simulates human intelligence and problem-solving capabilities (IBM, 2024a). In the age of Big Data, AI plays a crucial role, particularly through the use of machine learning and deep learning. The first is widely recognized as a branch of artificial intelligence emphasizing the use of data and algorithms to imitate how humans learn (IBM, 2024c). The latter is a subset of machine learning that uses multi-layered neural networks - deep neural networks - to simulate the complex decision-making power of the human brain (IBM, 2024b). These disciplines involve the development of AI algorithms, modeled after the decision-making processes of the human brain, that can ‘learn’ from available data and make increasingly more accurate classifications or predictions over time (IBM, 2024a).
The spatiotemporal behaviour term “can be defined as the sequence of attractions visited by tourists within a geographic space and the respective movements between an attraction and another in that geographic space (…) [and] it is described by spatial and temporal references and by attributive components, such as the nature of the place visited, time of arrival at attractions or the respective length of stay” (Caldeira & Kastenholz, 2022, p.196). Based on these definitions, the practical applications of AI in studies on tourists' STB seem very obvious. AI can be very useful, not only from the perspective of the tourist, i.e., supporting the visit, but also from the perspective of the researcher, since it can play a relevant role in the way georeferenced information on visitor movements is collected and in the way this information is processed and analysed to recognize movement patterns, to understand the tourists’ decision-making process, among others.