Confounds and Consequences in Geotagged Twitter Data

By Umashanthi Pavalanathan, Jacob Eisenstein. 2015

105 citations recorded by the source corpus.

Twitter is often used in quantitative studies that identify geographically-preferred topics, writing styles, and entities. These studies rely on either GPS coordinates attached to individual messages, or on the user-supplied location field in each profile. In this paper, we compare these data acquisition techniques and quantify the biases that they introduce; we also measure their effects on linguistic analysis and text-based geolocation. GPS-tagging and self-reported locations yield measurably different corpora, and these linguistic differences are partially attributable to differences in dataset composition by age and gender. Using a latent variable model to induce age and gender, we show how these demographic variables interact with geography to affect language use. We also show that the accuracy of text-based geolocation varies with population demographics, giving the best results for men above the age of 40.

Subfields: Communication, Statistical and Nonlinear Physics, Transportation

How researchers see this paper

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

In Communication

In Statistical and Nonlinear Physics

In Transportation

Citations in the corpus

Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019, methodology): “(see, e.g., Cohen and Ruths, 2013; Nguyen et al., 2014; Jurgens et al., 2015b; Pavalanathan and Eisenstein, 2015).”
Computational Sociolinguistics: A Survey (2016, background): “Pavalanathan and Eisenstein (2015b) compared geotagged tweets with tweets written by users with self-reported locations in their profile.”
Demographic Dialectal Variation in Social Media: A Case Study of African-American English (2016, background): “Geo-located users are a particular sample of the userbase (Pavalanathan and Eisenstein, 2015), but we expect it is reasonable to compare users of different races within this group.”
Geolocation for Twitter: Timing Matters (2016, result): “Our study is similar to that of Pavalanathan and Eisenstein (2015), who called into question the accuracy of geolocation models due to mismatches be-tween the behavior of users in available training data as compared to users encountered in live data.”
Studying User Income through Language, Behaviour and Affect in Social Media (2015, background): “…are not geolocated, as this would decrease our dataset size drastically — only 1 – 2% tweets or users are geolocated and represent a biased sample [56], profile field geolocation is not perfect or very frequent [57] and automatic geolocation prediction methods [58] would introduce biases in our…”
Fake news on Twitter during the 2016 U.S. presidential election (2019, unknown): “Previous work has found that self-reported locations are quite consistent with locations obtained through other methods, such as geo-tagged tweets or time zones (31, 32).”