Human-computer interaction for recursive prompt and image generation on media narratives of violence in Mexico
Year: 2026
Type: article
Abstract: Introduction This study explores media narratives of violence in Mexico through a hybrid human-computer interaction workflow combining computational analysis, human interpretation and generative artificial intelligence. Methods A non-probability corpus of 105 news items was analyzed to identify recurring terms, actors, locations and semantic relationships. Corpus summaries informed a workshop with 15 participants, who developed definitions and recursively refined text prompts and AI-generated images across five iterations. Textual and visual changes were analyzed, and experts supported their synthesis into an infographic and video. Results The selected corpus and workshop materials showed variation in textual and visual representations. Computational summaries made selected semantic differences explicit, while participants and experts supplied contextual interpretation. The process produced an infographic and video integrating these materials. Discussion The exploratory design does not estimate population parameters or establish causal effects. The workflow illustrates a human-led collaborative approach informed by mixed-initiative design: computational methods support structured comparison and generative variation, while people provide interpretation and critical judgment.
Source: Frontiers in Computer Science
Authors: Roman Anselmo Mora-Gutiérrez(Conceptualization, Methodology, Supervision, Writing – original draft, Writing – review & editing), Yadira Alatriste-Martinez(Data curation, Formal analysis, Visualization, Writing – review & editing), Oscar Antonio Manzanarez-Betancourt(Software, Writing – review & editing), Luis Angel Meza-Zarate(Formal analysis, Validation, Writing – review & editing), Edwin Montes-Orozco(Writing – review & editing), Gilberto Sinuhe Torres Cockrell
Language: English
Subfield: General Social Sciences
Field: Social Sciences
Domain: Social Sciences
Open Access status: gold
Estimated APC paid: $1,418
OpenAlex ID: W7235884071
