Against the background of increased interest in subjectively experienced well-being in economics, psychology, and the social sciences, this article analyzes how such well-being is associated with geographical context, social contacts, and life circumstances. The empirical analysis of data collected in Hong Kong is used to elaborate and support two main claims. The first is that geography matters to not only overall well-being but also momentary well-being and that researchers should be careful to specify the influence of geographical context correctly. We therefore employ an approach that is informed by various strands of time–geographical thought and find that life satisfaction is associated more strongly with geographical context than is momentary well-being. Second, we confirm positive relations between social contacts and experienced well-being but extend earlier research by showing that these relations stretch across multiple timescales and depend to some extent on the duration of an activity episode and with whom the activity episode is undertaken. This means that the use of simple indicators of social capital is inadequate for making the complex linkages between well-being and people's social contacts understandable in empirical research.

The widespread development of gated communities has generated much concern over urban fragmentation and social segregation. The social division and segregation between residents inside and outside urban enclaves exist not only in their residential spaces, but also in their values, social relations, and daily lives. In this study, it is argued that sociospatial segregation research should pay more attention to individuals' actual usage of urban space in their daily lives. By examining the activity space of the residents from different types of neighborhoods, a spatiotemporal approach to studying sociospatial segregation in Beijing, China is described. Significant differences are found in the usage of time and space between residents inside and outside the so-called privileged enclaves. Their activity spaces are found to vary significantly in terms of extensity, intensity, and exclusivity. The study suggests that the fragmentation of urban space is the result not only of residential segregation, but also of...

Understanding the relationship between short-term subway ridership and its influential factors is crucial to improving the accuracy of short-term subway ridership prediction. Although there has been a growing body of studies on short-term ridership prediction approaches, limited effort is made to investigate the short-term subway ridership prediction considering bus transfer activities and temporal features. To fill this gap, a relatively recent data mining approach called gradient boosting decision trees (GBDT) is applied to short-term subway ridership prediction and used to capture the associations with the independent variables. Taking three subway stations in Beijing as the cases, the short-term subway ridership and alighting passengers from its adjacent bus stops are obtained based on transit smart card data. To optimize the model performance with different combinations of regularization parameters, a series of GBDT models are built with various learning rates and tree complexities by fitting a maximum of trees. The optimal model performance confirms that the gradient boosting approach can incorporate different types of predictors, fit complex nonlinear relationships, and automatically handle the multicollinearity effect with high accuracy. In contrast to other machine learning methods—or “black-box” procedures—the GBDT model can identify and rank the relative influences of bus transfer activities and temporal features on short-term subway ridership. These findings suggest that the GBDT model has considerable advantages in improving short-term subway ridership prediction in a multimodal public transportation system.