More and more tourists are sharing their experiences on their social media through a combination of photos, texts, and hashtags. But there is a scarcity of studies in literature on analyzing tourists’ visual content in relation to tourism destinations. To address this gap in literature, this study explores how and with whom users express the greatest happiness in holiday destinations, and how they share it with their community, through a mixed methods approach composed of analysis of images, text, and metadata. This approach allows us to address the objective of this research, which is the prediction of the happiness felt by tourists during their experience, using innovative techniques that allow the independent variables to be obtained. To predict tourist satisfaction, two sources of data, photos and texts, are analyzed: a novel approach and little explored in the literature, but necessary due to the interaction of both variables. This study applies various artificial intelligence analyses on visual content (deep learning), and textual and metadata content (machine learning) to 39,235 Instagram posts shared by tourists since the emergence of Instagram thirteen years ago, at a cultural and gastronomic tourist destination. The findings of the visual content analysis showed that socialization and company, that is, traveling and interacting with people, was a key aspect of a positive tourism experience. In addition, the gender of the people with whom they traveled, and the tourist’s narcissism were also key aspects in the generation and expression of positive emotions. Regarding the analysis of the textual content, the results showed that when tourists enjoyed a positive experience, they became more involved in the generation of content, that is, they showed their happiness through positive words.