Identifying Unknown Locations and Demography based Sentiment Analysis

Big Data Analytics in Geo-Spatial metadata is geographically annotated social media is extremely valuable for modern information retrieval. However, when researchers can only access publicly-visible data, one quickly finds that social media users rarely publish location information. In this work, we provide a method which can geo-locate the over whelming majority of active Social media users, independent of their location sharing preferences, using only publicly-visible user data. My method infers an unknown user's location by examining their friend's locations. We frame the problem of identifying the location and optimization over a social network with a total variation based objective and provide a scalable and distributed algorithm for its solution. Furthermore, we show how a robust estimate of the geographic dispersion of each user's ego network can be used as a per-user accuracy measure, allowing us to discard poor location inferences and control the overall error of our approach and finally the sentimental analysis of the obtained user’s data over social media with user history statistics.