A importância do ambiente urbano para o bem-estar: Análise em Lisboa – Portugal - utilizando redes sociais

Abstract

Mental health problems have been rising worldwide, possibly associated with urban population growth and related lifestyles. The recognition that the various aspects of the urban environment can affect the mental health of individuals has been increasing since they are responsible for facilitating or inhibiting behaviors and lifestyles that impact the feeling. In this context, it is essential to understand the potential impact of the urban environment of the city of Lisbon. To do so, we resorted to sentiment analysis, using a lexicon from the NRC Sentiment and Emotion, based on data from the social network X, enabling the identification of places where both positive and negative sentiment prevail. Next, an machine learning (ML) model associated with an agnostic model was used to increase the understanding of the factors of the urban environment that can explain the sentiment. Four ML models were tested, Random Forest (RF), Extreme Gradient Boosting (XGBoost), Neural Network (NN), K-Nearest Neighbour (KNN), and a linear model for comparison (Generalized Linear Model - GLM). The agnostic models applied, the Local Interpretable Model Agnostic Explanations (LIME) and the Shapley Additive exPlanation (SHAP), played a crucial role in this study. Answering the starting question, the explanatory variables most related to sentiment are distance to fitness facilities, distance to green spaces, the popularity of locations (estimated through the social network Flickr), and distance to the cycling network.