Where in the World Are You? Geolocation and Language Identification in Twitter*

By Mark Graham, Scott A. Hale, Devin Gaffney. 2013

343 citations recorded by the source corpus.

The movements of ideas and content between locations and languages are unquestionably crucial concerns to researchers of the information age, and Twitter has emerged as a central, global platform on which hundreds of millions of people share knowledge and information. A variety of research has attempted to harvest locational and linguistic metadata from tweets to understand important questions related to the 300 million tweets that flow through the platform each day. Much of this work is carried out with only limited understandings of how best to work with the spatial and linguistic contexts in which the information was produced, however. Furthermore, standard, well-accepted practices have yet to emerge. As such, this article studies the reliability of key methods used to determine language and location of content in Twitter. It compares three automated language identification packages to Twitter's user interface language setting and to a human coding of languages to identify common sources of disagreement. The article also demonstrates that in many cases user-entered profile locations differ from the physical locations from which users are actually tweeting. As such, these open-ended, user-generated profile locations cannot be used as useful proxies for the physical locations from which information is published to Twitter.

Subfields: Artificial Intelligence, Geography, Planning and Development, Transportation

How researchers see this paper

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

In Artificial Intelligence

In Geography, Planning and Development

In Transportation

Citations in the corpus

Challenges of studying and processing dialects in social media (2015, background): “See Graham et al. (2014) for discussion. often explained by geographical diffusion.”
Processing Social Media Messages in Mass Emergency (2014, background): “Attaching geographical coordinates to a message (a process known as geotagging) is useful for a number of tasks in disaster response [Graham et al. 2014; Ikawa et al. 2013; Lingad et al. 2013].”
Room to Glo: A Systematic Comparison of Semantic Change Detection Approaches with Word Embeddings (2019, methodology): “We use the Compact Language Detector version 2 (CLDv2), 3 following guidance from Graham et al. (2014), and we discard any tweets for which CLD detects less than 90% of the text to be in English, resulting in roughly 2.5 billion tweets.”
Population Bias in Geotagged Tweets (2015, background): “However, these findings come from interpretations of distributions and county-level cartograms, rather than from statistical testing, and they rely on the user-defined 'location' field, which has been shown to have many inconsistencies (Graham, Hale, and Gaffney 2014; Hecht et al. 2011).”
Social Media data: Challenges, opportunities and limitations in urban studies (2019, background): “Practitioners argue that social media offers different visions on diverse aspects of social, economic and political urban life reflected by the user's interests and activities (Bawa-Cavia, 2011; Cerrone, 2015; Graham, Hale, & Gaffney, 2014; Huang & Wong, 2015).”
Everyone's Invited: A New Paradigm for Evaluation on Non-Transferable Datasets (2015, methodology): “Many social media analyses have used location meta-data to examine spatial phenomena such as well-being (Schwartz et al. 2013), language variation (Graham, Hale, and Gaffney 2014), topical discussions (Strnadova, Jurgens, and Lu 2013), and disaster response (Lingad, Karimi, and Yin 2013).”