Identifying Locations of Social Significance: Aggregating Social Media Content to Create a New Trust Model for Exploring Crowd Sourced Data and Information

Abstract

Most Internet content is no longer produced directly by corporate organizations or governments. Instead, individuals produce voluminous amounts of informal content in the form of social media updates (micro blogs, Facebook, Twitter, etc.) and other artifacts of community communication on the Web. This grassroots production of information has led to an environment where the quantity of low-quality, non-vetted information dwarfs the amount of professionally produced content. This is especially true in the geospatial domain, where this information onslaught challenges Local and National Governments and Non-Governmental Organizations seeking to make sense of what is happening on the ground.

This paper proposes a new model of trust for interpreting locational data without a clear pedigree or lineage. By applying principles of aggregation and inference, it is possible to identify locations of social significance and discover “facts” that are being asserted by crowd sourced information.