2016/03/10 by Nabil Hossain, Hossain, Nabil, Tianran Hu +9 · 1 citation
Medicine · Physics and Astronomy · Social Sciences · #Artificial Intelligence (cs.AI) #Complex Network Analysis Techniques #Crime Patterns and Interventions #Data-Driven Disease Surveillance #FOS: Computer and information sciences #Human Mobility and Location-Based Analysis #Social and Information Networks (cs.SI) #Substance Abuse Treatment and Outcomes
paper · pdf · doi:10.48550/arxiv.1603.03181
openalex publication_date 2016/03/10 · openalex created_date 2022/08/28 · openalex updated_date 2026/07/28
Nearly all previous work on geo-locating latent states and activities from\nsocial media confounds general discussions about activities, self-reports of\nusers participating in those activities at times in the past or future, and\nself-reports made at the immediate time and place the activity occurs.\nActivities, such as alcohol consumption, may occur at different places and\ntypes of places, and it is important not only to detect the local regions where\nthese activities occur, but also to analyze the degree of participation in them\nby local residents. In this paper, we develop new machine learning based\nmethods for fine-grained localization of activities and home locations from\nTwitter data. We apply these methods to discover and compare alcohol\nconsumption patterns in a large urban area, New York City, and a more suburban\nand rural area, Monroe County. We find positive correlations between the rate\nof alcohol consumption reported among a community's Twitter users and the\ndensity of alcohol outlets, demonstrating that the degree of correlation varies\nsignificantly between urban and suburban areas. While our experiments are\nfocused on alcohol use, our methods for locating homes and distinguishing\ntemporally-specific self-reports are applicable to a broad range of behaviors\nand latent states.\n