Assessing travel-related Quality of Life (QoL) is a significant challenge due to its reliance on subjective human perception, which is difficult to measure. Traditional studies are often constrained by the limited scope of costly, manual data collection. The significant contribution of this research is the introduction of a new framework that can analyze tourist perception on a large and systematic scale. The novelty of this work lies in the utilization of Google Street View (GSV) as a large-scale visual data source, coupled with the use of a sequence-based model to analyze travel routes, which allows for the simulation of the ever-changing travel experience better than the analysis of single, static images. This framework was applied to a dataset in Phuket, consisting of 456 driving routes, totaling 4,560 sequential images. Visual features were extracted from this image data using Object Detection and Semantic Segmentation techniques and then used to build prediction models with LSTM and KNeighborsRegressor for analysis in conjunction with QoL scores from questionnaires. The analysis revealed key insights into tourist perception patterns, identifying a significant divergence between the culturally homogeneous group of Thai tourists and the highly diverse group of foreign tourists. Furthermore, it was found that tangible quality of life dimensions (e.g., Material Well-being) was perceived more consistently than abstract dimensions (e.g., Emotional Well-being). In conclusion, this research shifts the paradigm of route analysis from focusing solely on efficiency to a human-centric process, providing a new tool for urban planners and stakeholders to understand and improve the quality of the journey in a more profound way.
Prakaisak et al. (Sun,) studied this question.