IDEIA: A Generative AI-Based System for Real-Time Editorial Ideation in Digital Journalism
June 08, 2025 Β· Declared Dead Β· π arXiv.org
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Victor B. Santos, CauΓ£ O. JordΓ£o, Leonardo J. O. Ibiapina, Gabriel M. Silva, Mirella E. B. Santana, Matheus A. Garrido, Lucas R. C. Farias
arXiv ID
2506.07278
Category
cs.HC: Human-Computer Interaction
Citations
0
Venue
arXiv.org
Last Checked
5 months ago
Abstract
This paper presents IDEIA (Intelligent Engine for Editorial Ideation and Assistance), a generative AI-powered system designed to optimize the journalistic ideation process by combining real-time trend analysis with automated content suggestion. Developed in collaboration with the Sistema Jornal do Commercio de ComunicaΓ§Γ£o (SJCC), the largest media conglomerate in Brazil's North and Northeast regions, IDEIA integrates the Google Trends API for data-driven topic monitoring and the Google Gemini API for the generation of context-aware headlines and summaries. The system adopts a modular architecture based on Node.js, React, and PostgreSQL, supported by Docker containerization and a CI/CD pipeline using GitHub Actions and Vercel. Empirical results demonstrate a significant reduction in the time and cognitive effort required for editorial planning, with reported gains of up to 70\% in the content ideation stage. This work contributes to the field of computational journalism by showcasing how intelligent automation can enhance productivity while maintaining editorial quality. It also discusses the technical and ethical implications of incorporating generative models into newsroom workflows, highlighting scalability and future applicability across sectors beyond journalism.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Human-Computer Interaction
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Improving fairness in machine learning systems: What do industry practitioners need?
R.I.P.
π»
Ghosted
Identifying Stable Patterns over Time for Emotion Recognition from EEG
R.I.P.
π»
Ghosted
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
R.I.P.
π»
Ghosted
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
R.I.P.
π»
Ghosted
Educational data mining and learning analytics: An updated survey
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted