The Keyword Explorer Suite: A Toolkit for Understanding Online Populations

TL;DR

This paper introduces a Python toolkit that leverages large language models to identify, validate, and analyze social media data, enabling detailed insights into online populations through keyword generation, content analysis, and model fine-tuning.

Contribution

It presents a novel pipeline combining GPT-3 and GPT-2 for population analysis, including keyword generation, content validation, and latent information exploration.

Findings

Effective identification of relevant social media content

Enhanced understanding of population subgroups online

Open-source toolkit for population analysis

Abstract

We have developed a set of Python applications that use large language models to identify and analyze data from social media platforms relevant to a population of interest. Our pipeline begins with using OpenAI's GPT-3 to generate potential keywords for identifying relevant text content from the target population. The keywords are then validated, and the content downloaded and analyzed using GPT-3 embedding and manifold reduction. Corpora are then created to fine-tune GPT-2 models to explore latent information via prompt-based queries. These tools allow researchers and practitioners to gain valuable insights into population subgroups online. Source code at https://github.com/pgfeldman/KeywordExplorer