The problem of understanding people's participation in real-world events has been a subject of active research and can offer valuable insights for human behavior analysis and event-related recommendation/advertisement. In this work, we study the latent factors for determining event popularity using large-scale datasets collected from the popular Meetup.com EBSN in three major cities around the world. We have conducted modeling analysis of four contextual factors (spatial, group, temporal, and semantic), and also developed a group-based social influence propagation network to model group-specific influences on events. By combining the Contextual features And Social Influence Network, our integrated prediction framework CASINO can capture the diverse influential factors of event participation and can be used by event organizers to predict/improve the popularity of their events. Evaluations demonstrate that our CASINO framework achieves high prediction accuracy with contributions from all the latent features we capture.