This research project investigates the potential of extracting emotions ( Safety, Comfort and Health) through text data from review based social media platforms. By implementing Natural Language Processing techniques as well as the development of a Classification and Regression Analysis model trained by a public web survey, the emotions are quantified through the identification of causal relationships between urban indicators related to Accessibility, Visibility, Circulation and Infrastructure. The machine learning models are then integrated into a digital workspace where the selected urban indicators are able to be manipulated in order to predict the emotion landscape. The result of this research proves the potential to evaluate and simulate emotions by using quantified data from the urban environment.