Digital humanities applied to the analysis of journalistic podcasts: an approach to research using AI agents

Vol. 24, 2026 - 346237
Coordinated Session
Favorite this paper
How to cite this paper?
Abstract

Digital humanities make it possible to analyze large volumes of data and perceive, from computational analysis built with natural language processing, patterns inscribed in digital traces. In this article, we analyze from the perspective of distant reading the metadata of 1702 episodes of the journalistic podcast "O Assunto" and the transcription of 1122 episodes. The collection includes all episodes published up to the day of collection. The scraping was carried out on the Spotify API and the Spotify_scrapper library, using code written with the support of the Google Gemini Pro 3.1 artificial intelligence tool, and applied to the Spotipy library. The analysis of the metadata allows us to understand patterns of duration, number of sources and periodicity of the episodes. From the computer analysis of the title and description of the episodes, we identified the patterns of thematization adopted by the podcast in its history. 

 

Share your ideas or questions with the authors!

Did you know that the greatest stimulus in scientific and cultural development is curiosity? Leave your questions or suggestions to the author!

Sign in to interact

Have a question or suggestion? Share your feedback with the authors!

Institutions
  • 1 Universidade Federal de Ouro Preto (UFOP)
  • 2 Universidade Federal de Ouro Preto
Area of Evaluation
  • RADIOJOR - Produção jornalística sonora em reconfiguração: técnicas, plataformas e formatos – Sessão 4
Keywords
Podcasting
Digital Humanities
research with AI agents
Thematization
O Assunto