Artificial intelligence methods to support the research of destination image in tourism. A systematic review

Destination Image can be considered as both, a theoretical and practical tool, to better understand how a destination is perceived in the minds of potential visitors. Given the im- pressive growth of digital sources of tourism-related data in the last decades, methods that exploit this information have been designed to explore this construct. Due to its capacity to emulate human intelligence and its ability to uncover hidden patterns, Arti?cial Intelligence has captured the attention of the academic and business sectors, for this reason, several ap- proaches from tourism research take advantage of such techniques. However, to date, there is neither sufficient information about what speci?c methods are being employed nor an eval- uation of their usefulness for the task. In this work, we identify the main techniques, as well as the representations, measurements, and results derived from the computational science perspective related to destination image in tourism studies. As a result, two taxonomies emerged: one related to the group of methods and techniques, and the other pertaining to the results obtained through these particular methodological designs. From our analysis, we found that electronic information is gaining strength as a primary information source, how- ever, our results showed that surveys are still on the top. On the other hand, the preferred techniques for information analysis are based on word frequencies but with a growing trend in the use of neural networks and deep learning techniques.