This paper proposes a method that allows the clustering and identification of similarities between users of a digital tourism platform, through the extraction of the sentiments expressed by them in the reviews or comments registered and the subsequent automatic clustering of the users, according to the polarity of sentiments subjectively expressed in their posts. This research fills a gap in the text mining literature for the development, improvement and/or reorientation of services and products in the field of tourism, providing a method to explore the needs and desires of the client based on their digital footprint drawn from posts and reviews about the service or product in question. The sentiment analysis is detailed, comprehending language detection and some specific language syntax treatment, with a subsequent explanation of the clustering algorithm used. The developed algorithm was tested in the user’s segmentation and sentiment analysis of their publications on a digital tourism platform. The results obtained demonstrate the efficiency of the solution, which presents a high accuracy in the classification of publications in four different languages and in the user’s segmentation process.