Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Using GPT Models for Qualitative and Quantitative News Analytics in the 2024 US Presidental Election Process

Bohdan M. Pavlyshenko

TL;DR

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.

Abstract

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.

Using GPT Models for Qualitative and Quantitative News Analytics in the 2024 US Presidental Election Process

TL;DR

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.

Abstract

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.

Paper Structure

This paper contains 24 sections, 1 equation, 15 figures.

Table of Contents

  1. Introduction
  2. Methodology
  3. Qualitative Results
  4. Results grouped by time periods
  5. Dates: 2024-08-01 -- 2024-08-15
  6. Dates: 2024-08-16 -- 2024-08-31
  7. Dates: 2024-09-01 -- 2024-09-15
  8. Dates: 2024-09-16 -- 2024-09-30
  9. Dates: 2024-10-01 -- 2024-10-15
  10. Results grouped by web resources
  11. Web resource: Web sites
  12. Web resource: The New York Times
  13. Web resource: CNN
  14. Web resource: The Washington Post
  15. Web resource: Fox News
  16. ...and 9 more sections

Figures (15)

  • Figure 1: Candidates' positive scores for time periods
  • Figure 2: Candidates' negative scores for time periods
  • Figure 3: Harris' positive sentiments scores in web resources
  • Figure 4: Trump's positive sentiments scores in web resources
  • Figure 5: Harris' negative sentiments scores in web resources
  • ...and 10 more figures