Omar Juárez Gambino
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Omar Juárez Gambino has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Hiram Calvo
Centro de Investigacion en Computacion, Instituto Politecnico Nacional, Mexico City, Mexico
6 shared publications - Consuelo Varinia García Mendoza
Instituto Politécnico Nacional, ESCOM
4 shared publications - Cesar Macias
Laboratorio de Ciencias Cognitivas Computacionales, Centro de Investigación en Computación, Instituto Politécnico Nacional
2 shared publications Diana Jimenez
Inst Politecn Nacl, Ctr Invest Comp, Mexico City, DF, Mexico
2 shared publications- Giovanni Guzmán
Centro de Investigación en Computación (CIC), Instituto Politécnico Nacional (IPN), UPALM-Zacatenco, Mexico City 07320, Mexico
2 shared publications Hiram Calvo
Laboratorio de Ciencias Cognitivas Computacionales, Instituto Politécnico Nacional
2 shared publications
Latest Publications
- Open Access
- 25 March 2026
- Published by MDPI AG in Information
- Vol. 17 (4) , 319
A Modular Approach to Automated News Generation Using Large Language Models
Advances in Generative Artificial Intelligence have enabled the development of models capable of generating text, images, and audio that are similar to what humans can create. These models often have valuable general knowledge thanks to their training on large datasets. Through fine-tuning or prompt-based adaptation, this knowledge can be applied to specific tasks. In this work, we propose a modular approach to automated news generation using Large Language Models, composed of an information retrieval module and a text generation module. The proposed system leverages both publicly available (open-weight) and proprietary Large Language Models, enabling a comparative evaluation of their behavior within the proposed news generation pipeline. We describe the experiments carried out with a total of five representative Large Language Models spanning both categories, detailing their configurations and performance. The results demonstrate the feasibility of using Large Language Models to automate this task and identify systematic differences in behavior across model categories, as well as the problems that remain to be solved to enable fully autonomous news generation.
- 25 March 2026
- Published by MDPI AG in Information
- Vol. 17 (4) , 319
Open AccessA Modular Approach to Automated News Generation Using Large Language Models
Advances in Generative Artificial Intelligence have enabled the development of models capable of generating text, images, and audio that are similar to what humans can create. These models often have valuable general knowledge thanks to their training on large datasets. Through fine-tuning or prompt-based adaptation, this knowledge can be applied to specific tasks. In this work, we propose a modular approach to automated news generation using Large Language Models, composed of an information retrieval module and a text generation module. The proposed system leverages both publicly available (open-weight) and proprietary Large Language Models, enabling a comparative evaluation of their behavior within the proposed news generation pipeline. We describe the experiments carried out with a total of five representative Large Language Models spanning both categories, detailing their configurations and performance. The results demonstrate the feasibility of using Large Language Models to automate this task and identify systematic differences in behavior across model categories, as well as the problems that remain to be solved to enable fully autonomous news generation.
- 18 October 2025
- Published by Springer Nature
- p. 89-106
Social Sensing of Fuel Theft: Open Data Analysis During the Mexican Petroleum Crisis
- 18 October 2025
- Published by Springer Nature
- p. 89-106
Social Sensing of Fuel Theft: Open Data Analysis During the Mexican Petroleum Crisis
- Open Access
- 27 March 2025
- Published by Manuscript Technomedia LLP in Journal of Scientometric Research
- Vol. 14 (1) , 351-364
Thesis Reviewer’s Committee Recommendation System
This paper presents a recommender system for the assignment of thesis reviewers at ESCOM-IPN Mexico. The system analyzes the thesis proposals, extracting relevant information and comparing it against the profiles of professors and courses given by the academic departments. The system determines the most suitable profiles and departments for the thesis review through a similarity evaluation. The results show that the system can generate accurate recommendations with a high degree of coincidence with the current process carried out by the committee in charge. In addition, the system performs an alternative process by suggesting reviewers with profiles more closely related to the thesis proposals considering additional information such as research papers and areas of expertise.
- 27 March 2025
- Published by Manuscript Technomedia LLP in Journal of Scientometric Research
- Vol. 14 (1) , 351-364
Open AccessThesis Reviewer’s Committee Recommendation System
This paper presents a recommender system for the assignment of thesis reviewers at ESCOM-IPN Mexico. The system analyzes the thesis proposals, extracting relevant information and comparing it against the profiles of professors and courses given by the academic departments. The system determines the most suitable profiles and departments for the thesis review through a similarity evaluation. The results show that the system can generate accurate recommendations with a high degree of coincidence with the current process carried out by the committee in charge. In addition, the system performs an alternative process by suggesting reviewers with profiles more closely related to the thesis proposals considering additional information such as research papers and areas of expertise.
- Open Access
- 19 November 2024
- Published by Elsevier in Data in Brief
- Vol. 57, 111158
Dataset of userʼs emotional reactions to news articles
- 19 November 2024
- Published by Elsevier in Data in Brief
- Vol. 57, 111158
Open AccessDataset of userʼs emotional reactions to news articles
- Open Access
- 23 February 2024
- Published by Elsevier in Data in Brief
- Vol. 53, 110220
Dataset of controversial news posts in Spanish from the reader's perspective
- 23 February 2024
- Published by Elsevier in Data in Brief
- Vol. 53, 110220
Open AccessDataset of controversial news posts in Spanish from the reader's perspective
- 27 December 2023
- Published by Instituto Politecnico Nacional/Centro de Investigacion en Computacion in Computación y Sistemas
- Vol. 27 (4) , 921-928
PoSLemma: How Traditional Machine Learning and Linguistics Preprocessing Aid in Machine Generated Text Detection
PoSLemma: How Traditional Machine Learning and Linguistics Preprocessing Aid in Machine Generated Text Detection
- 27 December 2023
- Published by Instituto Politecnico Nacional/Centro de Investigacion en Computacion in Computación y Sistemas
- Vol. 27 (4) , 921-928
PoSLemma: How Traditional Machine Learning and Linguistics Preprocessing Aid in Machine Generated Text Detection
PoSLemma: How Traditional Machine Learning and Linguistics Preprocessing Aid in Machine Generated Text Detection
- Open Access
- 23 October 2023
- Published by MDPI AG in Preprints.org
Analysis of Open-Social Data Behavior Concerning Gasoline Stealing: A Case Study of the Mexican Petroleum Crisis
At the beginning of 2019, the petroleum crisis impacted many economies dependent on this industry. The Mexican government started programs to identify points and government officials involved in the gasoline stealing from PEMEX (Petróleos Mexicanos), the country’s leading government petroleum company. The programs consisted of supervising and monitoring the Mexican country network of gasoline ducts to detect points where gasoline was being stolen. Consequently, large urban regions faced a lack and shortage of gasoline. This situation generated several reactions in social media and many open data in news media. Although the government provided open data about stealing gasoline locations related to crimes, it did not analyze the collected data to identify patterns, insights, and the spatio-temporal characterization of this phenomenon. This paper presents a study to deal with the regional semantics described in the social media locations of gasoline stealing. Thus, a framework to discover the trends that emerge from social media and how it is correlated with the government’s open data is also presented—the proposed methodology used machine learning techniques based on linguistic and semantic technologies. The analysis was applied to a dataset of 24,317 geo-referenced tweets. The obtained results reflected the Mexican thinking opinion regarding discovered social topics, polarization maps, and regional insights. According to discovered trends, there were long fuel lines between 1.5 and 5 kilometers (on average) at fuel stations in different Mexican states.
- 23 October 2023
- Published by MDPI AG in Preprints.org
Open AccessAnalysis of Open-Social Data Behavior Concerning Gasoline Stealing: A Case Study of the Mexican Petroleum Crisis
At the beginning of 2019, the petroleum crisis impacted many economies dependent on this industry. The Mexican government started programs to identify points and government officials involved in the gasoline stealing from PEMEX (Petróleos Mexicanos), the country’s leading government petroleum company. The programs consisted of supervising and monitoring the Mexican country network of gasoline ducts to detect points where gasoline was being stolen. Consequently, large urban regions faced a lack and shortage of gasoline. This situation generated several reactions in social media and many open data in news media. Although the government provided open data about stealing gasoline locations related to crimes, it did not analyze the collected data to identify patterns, insights, and the spatio-temporal characterization of this phenomenon. This paper presents a study to deal with the regional semantics described in the social media locations of gasoline stealing. Thus, a framework to discover the trends that emerge from social media and how it is correlated with the government’s open data is also presented—the proposed methodology used machine learning techniques based on linguistic and semantic technologies. The analysis was applied to a dataset of 24,317 geo-referenced tweets. The obtained results reflected the Mexican thinking opinion regarding discovered social topics, polarization maps, and regional insights. According to discovered trends, there were long fuel lines between 1.5 and 5 kilometers (on average) at fuel stations in different Mexican states.
- 23 October 2022
- Published by Springer Nature
- p. 137-147
Sentiment Analysis in the Rest-Mex Challenge
- 23 October 2022
- Published by Springer Nature
- p. 83-100
News Intention Study and Automatic Estimation of Its Impact
- 23 October 2022
- Published by Springer Nature
- p. 83-100
News Intention Study and Automatic Estimation of Its Impact