Human-computer interaction for recursive prompt and image generation on media narratives of violence in Mexico

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.

Authors

Institutions

Publication Details

Journal
Frontiers in Computer Science
Published
2026-11-18
DOI
https://doi.org/10.3389/fcomp.2026.1877314
Primary Topic
Computational and Text Analysis Methods
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Human-computer interaction for recursive prompt and image generation on media narratives of violence in Mexico

Yadira Alatriste-Martínez, Román Anselmo Mora-Gutiérrez, Edwin Montes-Orozco, Luis Angel Meza-Zarate et al.
2 links
Frontiers in Computer Science
Computational and Text Analysis Methods
article

Human-computer interaction for recursive prompt and image generation on media narratives of violence in Mexico

Yadira Alatriste-Martínez, Román Anselmo Mora-Gutiérrez, Edwin Montes-Orozco, Luis Angel Meza-Zarate, Oscar Antonio Manzanarez-Betancourt, Gilberto Sinuhe Torres Cockrell
article en

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.

Frontiers in Computer ScienceVol. 8
Universidad Autónoma Metropolitana (MX), Universidad de Ecatepec (MX), Tecnológico de Estudios Superiores de Ecatepec (MX), Universidad de las Américas Puebla (MX)
Computational and Text Analysis Methods
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon