Measuring the Convergence and Divergence in Urban Street Perception among Residents and Tourists through Deep Learning: A Case Study of Macau

Abstract

In today’s context of flourishing tourism, the development of urban tourism leads to a continuous influx of population. Existing empirical evidence highlights the interaction between tourists’ and residents’ perception of urban spaces and the local society and living spaces. This study, focusing on Macau, utilizes the region’s streetscape images to construct a deep learning-based model for quantifying the urban street perception of tourists and local residents. To obtain more refined perceptual evaluation data results, during the training phase of the model, we intentionally categorized tourist activities into natural landscape tours, historical sightseeing, and entertainment area visits, based on the characteristics of the study area. This approach aimed to develop a more refined perception evaluation method based on the classification of urban functional areas and the types of urban users. Further, to improve the streetscape environment and reduce visitor and resident dissatisfaction, we delved into the differences in perception between tourists and residents in various functional urban areas and their relationships with different streetscape elements. This study provides a foundational research framework for a comprehensive understanding of residents’ and tourists’ perceptions of diverse urban street spaces, emphasizing the importance of exploring the differentiated perceptions of streetscapes held by tourists and residents in guiding scientific urban tourism development policies and promoting social sustainability in cities, particularly those where tourism plays a significant role.