A Latent Variable Model for Geographic Lexical Variation

The rapid growth of geotagged social media raises new computational possibilities for investigating geographic linguistic variation. In this paper, we present a multi-level generative model that reasons jointly about latent topics and geographical regions. High-level topics such as "sports" or "entertainment" are rendered differently in each geographic region, revealing topic-specific regional distinctions. Applied to a new dataset of geotagged microblogs, our model recovers coherent topics and their regional variants, while identifying geographic areas of linguistic consistency. The model also enables prediction of an author's geographic location from raw text, outperforming both text regression and supervised topic models.

• Type: Journal
• Year: 2010
• Where: EMNLP
• Authors: Jacob Eisenstein, Brendan O'Connor, Noah A. Smith, Eric P. Xing
• Keywords: EMNLP 2010, Geographic Linguistic Variation, Multi-level Generative Model, Natural Language Processing, Topic-specific Regional Distinctions