OPOscar Peña-Cáceres

Oscar Peña-Cáceres

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Oscar Peña-Cáceres has a total of 53 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Deepfakes and bots in digital disinformation driven by malicious artificial intelligence

    by Oscar Peña-Cáceres, Mariela Chauca-Claros, Douglas Alvarado-Paiva, Darwin Aguilar-Chuquizuta, Henry Silva-Marchan

  • Open Access

    Agentic AI-Assisted Governance: Towards Semi-Autonomous State Oversight

    by Mariela Chauca-Claros, Oscar Peña-Cáceres, Elvis Garay-Silupu, Henry Silva-Marchan, Víctor Hugo Ramírez-Ordinola

    The detection of irregularities in public administration often takes weeks or months when it occurs at all. This article proposes a multi-agent framework based on agentic Artificial Intelligence (AI) for continuous, semi-autonomous, and systemic government oversight. The framework was developed from a literature review on agentic AI, algorithmic governance, and state oversight, and was structured into four functional layers and five specialized agents coordinated by a differentiated escalation mechanism that preserves human decision-making for the highest-impact findings. It was validated through a workshop involving 12 experts in public administration, AI, and auditing, applying Lawshe’s method and the MaxDiff technique to simulate scenarios of contract splitting and concealed budget diversion. The framework detected irregularities within 6 to 9 minutes, compared with weeks required by conventional audits, and achieved a content validity index of 0.85, supporting the relevance and consistency of the proposed framework. Thus, the study represents one of the first multi-agent reference frameworks to explicitly integrate agentic AI capabilities for continuous and semi-autonomous state oversight, applicable to the Latin American context, and opens future research avenues on pilot implementations, the legal framework governing evidentiary admissibility, and oversight of the auditing system itself.


  • Open Access

    AI-Driven Chatbots for Emergency and Disaster Response: A Global Bibliometric Analysis

    by Oscar Peña-Cáceres, Anthony Tavara-Ramos, Teófilo Correa-Calle, Manuel More-More

    The objective of this study is to analyze the global scientific production on the use of chatbots in emergencies and disaster response, identifying research trends, collaboration patterns, and thematic evolution. A bibliometric analysis was conducted using 97 documents indexed in Scopus between 2019 and July 2025. The analysis employed MASHA and VOSviewer to combine performance indicators with science mapping, enabling the visualization of research networks and emerging topics. Findings reveal an annual growth rate of 34.17%, encompassing 75 publication sources and 367 contributing authors, with a 100% co-authorship rate. Articles and conference papers account for 51.5% and 42.3% of the literature, with an average of 7.1 citations per document and an overall h-index of 15. The United States, China, and India lead global contributions, while keyword co-occurrence analysis indicates increasing interest in human-centered communication, coordination, and artificial intelligence applications. However, topics such as healthcare integration, crisis data management, and ethical governance remain underexplored. This study advances the field by systematizing a previously dispersed body of research, revealing the conceptual foundations and intellectual structure of chatbot applications in emergency contexts. By combining bibliometric evidence with a human-centered perspective, a comprehensive framework is introduced that assesses the ethical, social, and technological dimensions to develop resilient and reliable emergency response systems for the future.

  • Open Access

    Dynamic characterization of explanations during human–machine collaboration in cyber-physical systems

    by Oscar Peña-Cáceres, Antoni Mestre, Manoli Albert, Vicente Pelechano, Miriam Gil

    Cyber-Physical Systems often rely on human–machine collaboration to achieve superior outcomes and mutual learning. For effective collaboration, systems must be understandable and trustworthy. Explanations are instrumental in promoting system understandability and building human trust. However, crafting such explanations poses key challenges: How many explanations do users need? How much information can they process? What level of detail is appropriate? This work introduces a conceptual model to characterize explanations and a predictive model that determines when and what type of explanation to provide. The predictive model considers system context, user profile, and interaction behavior, using machine learning techniques to infer explanatory needs and tailor responses accordingly. Although we apply our approach to a smart home environment, the methodology is generalizable to other CPS domains. At design time, developers define possible explanation points and relevant parameters. At runtime, the system autonomously adapts explanations to user-specific conditions. To validate our proposal, we conducted an experimental study evaluating the resulting explanations in terms of understandability, obtrusiveness, and adaptability. Results showed modest but meaningful improvements in all three dimensions, suggesting that our framework facilitates explanation designs more aligned with user preferences and situational demands.

  • Open Access

    Automatic generation of explanations in autonomous systems: enhancing human interaction in smart home environments

    by Oscar Peña-Cáceres, Antoni Mestre, Manoli Albert, Vicente Pelechano, Miriam Gil

    In smart environments, autonomous systems often adapt their behavior to the context, and although such adaptations are generally beneficial, they may cause users to struggle to understand or trust them. To address this, we propose an explanation generation system that produces natural language descriptions (explanations) to clarify the adaptive behavior of smart home systems in runtime. These explanations are customized based on user characteristics and the contextual information derived from the user interactions with the system. Our approach leverages a prompt-based strategy using a fine-tuned large language model, guided by a modular template that integrates key data such as the type of explanation to be generated, user profile, runtime system information, interaction history, and the specific nature of the system adaptation. As a preliminary step, we also present a conceptual model that characterize explanations in the domain of autonomous systems by defining their core concepts. Finally, we evaluate the user experience of the generated explanations through an experiment involving 118 participants. Results show that generated explanations are perceived positive and with high level of acceptance.

  • Open Access

    Editorial

    by Oscar Peña-Cáceres

    Es un privilegio dar la bienvenida al primer número de International Journal of Computational Innovations, Intelligent Systems and AI, revista internacional arbitrada con registro ISSN 3084-7907 en su edición en línea. Este lanzamiento inaugura un foro de convergencia para la innovación computacional, la inteligencia artificial y el diseño de sistemas inteligentes, en un escenario global marcado por la vertiginosa evolución tecnológica y la imperiosa necesidad de soluciones disruptivas. Nuestra propuesta editorial nace con la vocación de acoger investigaciones que, sin renunciar al rigor metodológico, dialoguen con los desafíos concretos de la sociedad y la industria, estimulando un intercambio científico capaz de trascender fronteras geográficas y disciplinares. Con esta aspiración, nos proponemos consolidarnos como un referente internacional para quienes impulsan, desarrollan y aplican tecnologías emergentes con visión crítica y propósito transformador.


  • Open Access

    A Method for Estimating Time and Water Velocity: Case Study of the Piura River, Peru

    by Oscar Peña-Cáceres, Eduardo Arbulú-Gonzales, Manuel More-More, Rudy Espinoza-Nima, Henry Silva-Marchan

    El fenómeno “El Niño” afecta periódicamente a la región de Piura, en Perú, provocando fuertes lluvias que incrementan el caudal del río Piura y, en algunos casos, generan desbordamientos, como ocurrió en 2017. Este evento representa un riesgo latente para los habitantes de los distritos de Piura, Castilla, Catacaos y Cura Mori. El estudio tuvo como objetivo estimar el tiempo y la velocidad superficial del flujo de agua en cuatro segmentos del río Piura. Para ello, se utilizó la técnica del flotador, que consistió en medir el tiempo que tarda un objeto flotante en desplazarse entre puntos establecidos. Las mediciones se realizaron en los puentes Andrés Avelino Cáceres, Eguiguren, Sánchez Cerro, San Miguel y Bolognesi. La experimentación se limitó a caudales de magnitud baja, de acuerdo con las condiciones hidrometeorológicas presentes durante los meses de marzo de 2019 y 2021, lo cual otorga un carácter estimativo a los resultados obtenidos. Los hallazgos indican que, a medida que el caudal (m³/s) aumenta, disminuye el tiempo de recorrido de las masas de agua y la velocidad superficial se incrementa proporcionalmente. Por ejemplo, un caudal de 422 m³/s se asoció a una velocidad de 1,14 m/s, lo que implica que el agua tarda aproximadamente 28 minutos en recorrer los cuatro tramos evaluados.

  • Open Access

    Patrones Lingüísticos y Visuales de ChatGPT en la Educación Superior

    by Oscar Peña Cáceres, Elvis Sánchez-Rogel, Jhon Barros-Naranjo, Henry Silva-Marchan, Rudy Espinoza-Nima, Teofilo Correa-Calle

    Este artículo examina la influencia de la inteligencia artificial en la redacción académica, enfocándose en las tesis de grado. Su objetivo es identificar los patrones lingüísticos y visuales en textos generados o asistidos por ChatGPT, mediante un análisis de 50 tesis de pregrado y maestría, distribuidas equitativamente entre una universidad pública y una privada de Perú. Los resultados indican que las estructuras argumentativas más representativas incluyen términos como “además”, “papel crucial” y “exhaustiva”. Se observó un 48% de similitud argumentativa en la universidad pública, en contraste con el 72% en la universidad privada. Se recomienda ampliar el análisis con otros modelos de lenguaje, como BART.


  • Comparison of the VADER and TextBlob Models in Sentiment Analysis

    by Oscar Peña-Cáceres, Henry Silva-Marchan, Rudy Espinoza-Nima, Manuel More-More, Andrea Villegas-Paz


  • Open Access

    LLMs in the Generation of Seismic Alert Communiqués

    by Oscar Peña-Cáceres, Henry Silva-Marchan, Rudy Espinoza-Nima, Manuel More-More, Mariela Chauca-Claros, Jorge Yánez-Palacios

    Peru is in the Ring of Fire, a zone of high seismic activity. Currently, alerts generated by technical-scientific entities are often bland and lack precise geographic context, resulting in alerts of limited usefulness for informing the public. In this paper, we present a conceptual model and architecture to explore the potential of Large Language Models (LLMs) to produce various forms of seismic warnings tailored to the particularities that would be required for different geographic areas of a given locality in Peru. The proposal was evaluated in a controlled environment with the participation of 47 users with diverse ethnographic characteristics. The context of the study was explained to them, and they were provided with a questionnaire designed to assess the ease of understanding, usefulness and quality of the content of the alert communications generated by an LLM. The results show that, according to the indicators assessed, seismic warnings generated by an LLM are 76% easy to understand, 81% useful and 71% acceptable quality.