Based on a series of large scale surveys, this paper first analyzes the effects of social, demographical, and behavioral factors as well as long-term sound experience on the subjective evaluation of soundscape in urban open public spaces. Te paper then explores the feasibility of using computer-based artificial neural network to build models for predicting the soundscape quality evaluation of potential users in urban open spaces at the design stage. It has been shown that for both subjective sound level and acoustic comfort evaluation, a general model for all the case study sites is less feasible due to the complex physical and social environments in urban open spaces, models based on individual case study sites perform well but the application range is limited, and specific models for certain types of location/function would be reliable and practical. It is expected that such a model framework would be useful for the soundscape standardization, in terms of factors to be considered, for example.