A Comparative Analysis of Content-based Geolocation in Blogs and Tweets

TL;DR

This paper compares text-based geolocation methods on Blogger and Twitter, introducing new features that improve accuracy and analyzing factors affecting geolocability across different social media platforms and user demographics.

Contribution

It introduces novel location-specific features for geolocation, compares performance across Blogger and Twitter, and investigates cross-media and demographic effects on geolocability.

Findings

Error rate reduced by up to 12.5% with new features

Blogger users are harder to geolocate than Twitter users

Cross-media and demographic factors influence geolocability

Abstract

The geolocation of online information is an essential component in any geospatial application. While most of the previous work on geolocation has focused on Twitter, in this paper we quantify and compare the performance of text-based geolocation methods on social media data drawn from both Blogger and Twitter. We introduce a novel set of location specific features that are both highly informative and easily interpretable, and show that we can achieve error rate reductions of up to 12.5% with respect to the best previously proposed geolocation features. We also show that despite posting longer text, Blogger users are significantly harder to geolocate than Twitter users. Additionally, we investigate the effect of training and testing on different media (cross-media predictions), or combining multiple social media sources (multi-media predictions). Finally, we explore the geolocability of social media in relation to three user dimensions: state, gender, and industry.