2014/03/29 by Petko Georgiev, Georgiev, Petko, Anastasios Noulas +3
Engineering · Social Sciences · #Evacuation and Crowd Dynamics #FOS: Computer and information sciences #FOS: Physical sciences #Human Mobility and Location-Based Analysis #Physics and Society (physics.soc-ph) #Social and Information Networks (cs.SI) #Transportation Planning and Optimization
paper · pdf · doi:10.48550/arxiv.1403.7657
openalex publication_date 2014/03/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Understanding the social and behavioral forces behind event participation is\nnot only interesting from the viewpoint of social science, but also has\nimportant applications in the design of personalized event recommender systems.\nThis paper takes advantage of data from a widely used location-based social\nnetwork, Foursquare, to analyze event patterns in three metropolitan cities. We\nput forward several hypotheses on the motivating factors of user participation\nand confirm that social aspects play a major role in determining the likelihood\nof a user to participate in an event. While an explicit social filtering signal\naccounting for whether friends are attending dominates the factors, the\npopularity of an event proves to also be a strong attractor. Further, we\ncapture an implicit social signal by performing random walks in a high\ndimensional graph that encodes the place type preferences of friends and that\nproves especially suited to identify relevant niche events for users. Our\nfindings on the extent to which the various temporal, spatial and social\naspects underlie users' event preferences lead us to further hypothesize that a\ncombination of factors better models users' event interests. We verify this\nthrough a supervised learning framework. We show that for one in three users in\nLondon and one in five users in New York and Chicago it identifies the exact\nevent the user would attend among the pool of suggestions.\n