Seeing and thinking about urban blue‒green space: Monitoring public landscape preferences using bimodal data

Urban blue green spaces (UBGSs) are a significant avenue for addressing the global mental health crisis To effectively optimize landscape design and management for the promotion of health benefits from UGBS, it is crucial to objectively understand public preferences Utilizing biomodal data compared of images and text posted by park users on online review platforms, this study delves into sensitive incidents within UBGSs and explores differences and similarities in landscape preferences across both modalities The findings demonstrate variations in the population of different parks, yet overall, the public rates of their positivity There are differences in both the frequency and extent of perception of different landscape features between image and text modalities Among them, landscape elements involving stability are perceived to be a greater degree in the image modality than in the text modality, while the conversation is true for dynamic and experimental landscape elements In both modalities, the distinctive landscape features of parks are more frequently perceived and preferred by the public This research sheds light on divisions and connections within landscape perceptions across the two data modalities, offering an essential reference for future research on landscape perceptual preferences In addition, it provides suggestions for the design and management improvement of UBGSs and there consolidates its health benefits for urban residents