Learning about Spanish dialects through Twitter

TL;DR

This study uses geographically tagged Twitter data to map Spanish dialects worldwide, revealing urban dialects' international features and regional dialects' local uniformity through machine learning analysis.

Contribution

It introduces a large-scale, data-driven approach to mapping Spanish dialects using social media, highlighting urban versus rural linguistic variations.

Findings

Urban dialects have an international character.

Regional dialects show more local uniformity.

Large-scale Twitter data effectively captures dialectal variation.

Abstract

This paper maps the large-scale variation of the Spanish language by employing a corpus based on geographically tagged Twitter messages. Lexical dialects are extracted from an analysis of variants of tens of concepts. The resulting maps show linguistic variation on an unprecedented scale across the globe. We discuss the properties of the main dialects within a machine learning approach and find that varieties spoken in urban areas have an international character in contrast to country areas where dialects show a more regional uniformity.