Figshare· 2018
A Latent Variable Model for Geographic Lexical Variation
- 607citations
- 2018year
Short summary
A new multi-level generative model jointly reasons about latent topics and geographic regions, revealing topic-specific regional linguistic distinctions in geotagged microblogs.
AI-generated from the title and abstract; the full text is not read.
Key points
- A multi-level generative model jointly models latent topics and geographic regions.
- The model reveals topic-specific regional linguistic distinctions.
- It successfully recovers coherent topics and their regional variants from geotagged microblogs.
- The model identifies geographic areas of linguistic consistency.
- It predicts author geographic location from text, outperforming other models.
AI-generated from the title and abstract; the full text is not read.
Abstract
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.
The authors' abstract, as published at the source. Figshare, 2018 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Linguistics and Language
Linguistics and LanguageSocial Sciences