Tourism destination image based on tourism user generated content on internet

Purpose - The purpose of this paper is to study tourists' spatial and psychological involvement reflected through tourism destination image (TDI), TDI is divided into on-site and after-trip groups and the two groups are compared in the frame of three-dimensional continuums. Design/methodology/approach - By conducting latent Dirichlet allocation (LDA) modeling to tourism user-generated content. structural topic models are established. The topics separated out from unstructured raw texts are structural themes and representations of TDI. Social network analysis (SNA) reveals the quantitative and structural differences of three-dimensional continuums of the two TDI groups. Findings - The findings reveal that from the stage of on-site to after-trip, tourist perception of TDI shifts from psychologically to functionally-oriented, from common to unique, and from holistic to more attribute focused. Also, it is suggested that from a postmodemism perspective, TDI is never unique, fixed or universal. but has different image perceptions and feedbacks for different tourists. Research limitations/implications - With the assistance of social sensing, a panoramic view of TDI could be established. Targeted and precision destination marketing and image promotion could be applied out to each individual tourist. Originality/value - Combining with the perspectives of the tourist-destination space system and the tourism involvement theory, this research proposes a TDI transformation model and an explanation of the internal mechanism. The originality of research also lies in the methodological innovation of social sensing data and the LDA topic model.