Mason Archival Repository Service

Geo-Fingerprinting of Social Media Content

Show simple item record

dc.contributor.advisor Pfoser, Dieter Gazaz, Hatim
dc.creator Gazaz, Hatim 2016-04-22 2016-09-09T17:59:00Z 2016-09-09T17:59:00Z
dc.description.abstract With the percentage of Twitter users approaching 20% of the US population by 2019, tweets provide a good sample of the public’s sentiment and opinion. Consequently such data has been excessively used in commercial and research efforts. While works have analyzed the content of tweets in relation to the underlying social network of a discussion, somewhat less attention has been paid to the spatial distribution of messages and topics. This thesis tries to assess the locality of discussions using the concepts mentioned in tweets. Based on a global distribution of topics across the 48 contiguous states, spatial topic dissimilarity is discovered by recursively subdividing the space into smaller and smaller partitions and using statistical testing to compare the distributions. Experimenting with a large Twitter dataset for the US, locality of a discussion was observed to occur at specific thresholds and only 14 of the 49 most populous urban areas feature a unique discussion. Overall, this work establishes trends as to when locality in a discussion in social media occurs.
dc.language.iso en en_US
dc.subject social media en_US
dc.subject Twitter en_US
dc.subject geospatial en_US
dc.subject entity extraction en_US
dc.title Geo-Fingerprinting of Social Media Content en_US
dc.type Thesis en_US Master of Science in Geoinformation and Geospatial Intelligence en_US Master's en_US Geoinformation and Geospatial Intelligence en_US George Mason University en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search MARS


My Account