Computer supported analysis of Thailand’s imagery on Pinterest

Abstract

© 2019, © 2019 Informa UK Limited, trading as Taylor & Francis Group. This paper reports findings and introduces an innovative methodological approach deployed to explore how complex visual imagery on Pinterest represents Thailand and how commercial and private users differ in this respect. For this purpose, visual content analysis of 300 images was performed in which computer vision labelling and a subsequent manual thematic analysis were deployed during a two-step procedure. The obtained findings reveal that significant differences exist among both types of users regarding some frequently depicted themes (architecture, animals) and regarding textual, graphic and substantive content. These differences in turn inform the theoretical and practical implications for improved communication on social media. The limitations of the study are also discussed.