Geolocation Prediction in Social Media Data by Finding Location Indicative Words

216 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Simplifying Graph Convolutional Networks (2019, methodology): “All experiments on the GEOTEXT dataset are conducted on a single Nvidia GTX-1080Ti GPU while the ones on the TWITTER-NA and TWITTER-WORLD datasets are excuded with 10 cores of the Intel(R) Xeon(R) Silver 4114 CPU (2.20GHz).”
Predictive Analysis on Twitter: Techniques and Applications (2018, methodology): “(using doc2vec [79]), network features and topology (using node2vec [80]) and time-stamps to deduce users location. They achieved an accuracy over 60% for GeoText20, UTGeo1121 and 55% for TwitterWorld[81]. Furthermore, MENET achieves an accuracy of 76% in region classication and 64.4% in state class”
Computational Sociolinguistics: A Survey (2016, methodology): “While the topic of text-based location prediction has received increasing attention (Han, Cook, and Baldwin 2012; Wing and Baldridge 2011), using these models for the discovery of new sociolinguistic patterns is an option that has not been fully explored yet, since most studies primarily focus on…”