Text-Based Twitter User Geolocation Prediction

By Bo Han, Paul Cook, Timothy Baldwin. Journal of Artificial Intelligence Research, 2014

321 citations recorded by the source corpus.

Geographical location is vital to geospatial applications like local search and event detection. In this paper, we investigate and improve on the task of text-based geolocation prediction of Twitter users. Previous studies on this topic have typically assumed that geographical references (e.g., gazetteer terms, dialectal words) in a text are indicative of its author's location. However, these references are often buried in informal, ungrammatical, and multilingual data, and are therefore non-trivial to identify and exploit. We present an integrated geolocation prediction framework and investigate what factors impact on prediction accuracy. First, we evaluate a range of feature selection methods to obtain "location indicative words". We then evaluate the impact of nongeotagged tweets, language, and user-declared metadata on geolocation prediction. In addition, we evaluate the impact of temporal variance on model generalisation, and discuss how users differ in terms of their geolocatability. We achieve state-of-the-art results for the text-based Twitter user geolocation task, and also provide the most extensive exploration of the task to date. Our findings provide valuable insights into the design of robust, practical text-based geolocation prediction systems.

Subfields: Geography, Planning and Development, Transportation, Signal Processing

View Paper: https://www.semanticscholar.org/paper/4e2bf29fbbc4735f4a722ba56b53e8b6aab47b86

How researchers see this paper

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

In Geography, Planning and Development

In Transportation

In Signal Processing

Citations in the corpus

How Twitter is Changing the Nature of Financial News Discovery (2016, methodology): “This decision can be aided by methods that contextualize tweets [35], such as displaying inferred location [16, 20, 47, 9, 7, 28, 39, 14, 13] or topic context [29, 33].”
Geolocation for Twitter: Timing Matters (2016, methodology): “We matched each tweet to a city using the procedure of Han et al. (2014), with 3,709 cities derived from the geonames database 2 .”
Semi-supervised User Geolocation via Graph Convolutional Networks (2018, background): “…media (Eisen-stein et al., 2010; Hong et al., 2012; Ahmed et al., 2013); and (3) supervised models which are often framed as text classiﬁcation (Serdyukov et al., 2009; Wing and Baldridge, 2011; Roller et al., 2012; Han et al., 2014) or text regression (Iso et al., 2017; Rahimi et al., 2017a).”
Confounds and Consequences in Geotagged Twitter Data (2015, methodology): “A major application of geotagged social media is to predict the geolocation of individuals based on their text (Eisenstein et al., 2010; Cheng et al., 2010; Wing and Baldridge, 2011; Hong et al., 2012; Han et al., 2014).”
The Effect of Population and "Structural" Biases on Social Media-based Algorithms: A Case Study in Geolocation Inference Across the Urban-Rural Spectrum (2017, background): “[25]) is to invert the goals of this paper and attempt to find ways reduce the “geolocatability” of a person or a population (i.”
Social Media data: Challenges, opportunities and limitations in urban studies (2019, background): “This is because a tweet geocode can only be generated from GPS-enabled devices (Han, Cook, & Baldwin, 2014), and, even though users have full control of whether their tweets are geolocated or not, the geolocation option in the Twitter app is off by default.”
Detection and Resolution of Rumours in Social Media (2017, methodology): “…for this is to use alternative API endpoints to collect posts through a less restrictive stream of data, such as Twitter’s streaming API sampling a random 1% of the whole, or a ﬁlter of posts by geolocation, where available, to collect posts coming from a country or region [Han et al. 2014].”