Leveraging Large Language Models to Geolocate Linguistic Variations in Social Media Posts

TL;DR

This paper presents a method using fine-tuned large language models to accurately geolocate Italian social media posts by predicting both regional and coordinate information, advancing the state-of-the-art in linguistic geolocation.

Contribution

The study introduces a novel approach of fine-tuning LLMs specifically for Italian social media geolocalization, addressing both regional and precise coordinate prediction tasks.

Findings

Enhanced geolocalization accuracy over previous methods

Effective understanding of Italian social media linguistic nuances

Open-source code for reproducibility and further research

Abstract

Geolocalization of social media content is the task of determining the geographical location of a user based on textual data, that may show linguistic variations and informal language. In this project, we address the GeoLingIt challenge of geolocalizing tweets written in Italian by leveraging large language models (LLMs). GeoLingIt requires the prediction of both the region and the precise coordinates of the tweet. Our approach involves fine-tuning pre-trained LLMs to simultaneously predict these geolocalization aspects. By integrating innovative methodologies, we enhance the models' ability to understand the nuances of Italian social media text to improve the state-of-the-art in this domain. This work is conducted as part of the Large Language Models course at the Bertinoro International Spring School 2024. We make our code publicly available on GitHub https://github.com/dawoz/geolingit-biss2024.