2019/01/16 by Jacobo Levy Abitbol, Márton Karsai, Abitbol, Jacobo Levy +3
Physics and Astronomy · Social Sciences · #Complex Network Analysis Techniques #Computation and Language (cs.CL) #Computers and Society (cs.CY) #Data Analysis #FOS: Computer and information sciences #FOS: Physical sciences #Human Mobility and Location-Based Analysis #Opinion Dynamics and Social Influence #Physics and Society (physics.soc-ph) #Social and Information Networks (cs.SI) #Statistics and Probability (physics.data-an)
paper · pdf · doi:10.48550/arxiv.1901.05389
openalex publication_date 2019/01/16 · openalex created_date 2022/07/30 · openalex updated_date 2026/07/28
The socioeconomic status of people depends on a combination of individual\ncharacteristics and environmental variables, thus its inference from online\nbehavioral data is a difficult task. Attributes like user semantics in\ncommunication, habitat, occupation, or social network are all known to be\ndeterminant predictors of this feature. In this paper we propose three\ndifferent data collection and combination methods to first estimate and, in\nturn, infer the socioeconomic status of French Twitter users from their online\nsemantics. Our methods are based on open census data, crawled professional\nprofiles, and remotely sensed, expert annotated information on living\nenvironment. Our inference models reach similar performance of earlier results\nwith the advantage of relying on broadly available datasets and of providing a\ngeneralizable framework to estimate socioeconomic status of large numbers of\nTwitter users. These results may contribute to the scientific discussion on\nsocial stratification and inequalities, and may fuel several applications.\n