Using GPT Models for Qualitative and Quantitative News Analytics in the 2024 US Presidental Election Process
This provides a method for political analysts or researchers to gain insights from news data, but it is incremental as it applies existing techniques to a new domain.
The paper tackled analyzing news for the 2024 US presidential election by using GPT-4o with retrieval-augmented generation to generate quantitative scores, which were analyzed with Bayesian regression to derive trend lines and uncertainty distributions, demonstrating that this approach yields informative analytics for election processes.
The paper considers an approach of using Google Search API and GPT-4o model for qualitative and quantitative analyses of news through retrieval-augmented generation (RAG). This approach was applied to analyze news about the 2024 US presidential election process. Different news sources for different time periods have been analyzed. Quantitative scores generated by GPT model have been analyzed using Bayesian regression to derive trend lines. The distributions found for the regression parameters allow for the analysis of uncertainty in the election process. The obtained results demonstrate that using the GPT models for news analysis, one can get informative analytics and provide key insights that can be applied in further analyses of election processes.