Sergio Muñoz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sergio Muñoz has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Carlos A. Iglesias
ETSI Montes, Forestal y del Medio Natural, Universidad Politécnica de Madrid, Calle José Antonio Nováis, 10, 28040 Madrid, Spain
10 shared publications - Oscar Araque
Universidad Politécnica de Madrid
3 shared publications - Juan Fernando Sánchez Rada
Intelligent Systems Group, Universidad Politécnica de Madrid, 28040 Madrid, Spain
2 shared publications - Mauro Dragoni
Fondazione Bruno Kessler
2 shared publications - Álvaro Carrera
Universidad Politécnica de Madrid, Av. Complutense, 30, 28040, Madrid, Spain
2 shared publications - Andrei Scheianu
R&D Department, Beia Consult International, 041386 Bucharest, Romania
1 shared publication
Latest Publications
- 23 October 2026
- Published by Springer Nature
- p. 413-432
MIAO: A Mental Illness Analysis Ontology for Detecting Mental Health Conditions
- 23 October 2026
- Published by Springer Nature
- p. 413-432
MIAO: A Mental Illness Analysis Ontology for Detecting Mental Health Conditions
- 8 July 2026
- Published by Springer Nature
- p. 384-394
Assessing Mental Health Therapeutic Capacity in AI Agents
- 8 July 2026
- Published by Springer Nature
- p. 384-394
Assessing Mental Health Therapeutic Capacity in AI Agents
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 54127-54147
Effects of Interaction and Explanation Type on Human–AI Collaboration for Fake News Detection
AI-assisted decision-making systems are increasingly used across domains, prompting research into design factors that influence their effectiveness. Prior work has examined elements such as explanation type, interface design, and cognitive support interventions; however, the complexity of real-world tasks makes the generalization of findings difficult. In particular, in real-world decision-making settings like Fake News Detection studies on human-AI collaboration remain underexplored. This study investigates how explanation type and system interactivity affect human-AI collaboration in the context of fake news detection. In a controlled online experiment (N = 161), we varied the explanation type and the interactivity of an AI system that assists with the fake news detection task. Results show that conversational systems increased user reliance, while feature importance explanations appeared to be more effective than counterfactual explanations. These findings highlight the importance of explanation design and interaction modality in shaping effective AI-assisted decision-making in real world settings where underlying regularities are difficult for non-expert users to detect.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 54127-54147
Open AccessEffects of Interaction and Explanation Type on Human–AI Collaboration for Fake News Detection
AI-assisted decision-making systems are increasingly used across domains, prompting research into design factors that influence their effectiveness. Prior work has examined elements such as explanation type, interface design, and cognitive support interventions; however, the complexity of real-world tasks makes the generalization of findings difficult. In particular, in real-world decision-making settings like Fake News Detection studies on human-AI collaboration remain underexplored. This study investigates how explanation type and system interactivity affect human-AI collaboration in the context of fake news detection. In a controlled online experiment (N = 161), we varied the explanation type and the interactivity of an AI system that assists with the fake news detection task. Results show that conversational systems increased user reliance, while feature importance explanations appeared to be more effective than counterfactual explanations. These findings highlight the importance of explanation design and interaction modality in shaping effective AI-assisted decision-making in real world settings where underlying regularities are difficult for non-expert users to detect.
- Open Access
- 4 October 2024
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 8 (10) , 129
Exploiting Content Characteristics for Explainable Detection of Fake News
The proliferation of fake news threatens the integrity of information ecosystems, creating a pressing need for effective and interpretable detection mechanisms. Recent advances in machine learning, particularly with transformer-based models, offer promising solutions due to their superior ability to analyze complex language patterns. However, the practical implementation of these solutions often presents challenges due to their high computational costs and limited interpretability. In this work, we explore using content-based features to enhance the explainability and effectiveness of fake news detection. We propose a comprehensive feature framework encompassing characteristics related to linguistic, affective, cognitive, social, and contextual processes. This framework is evaluated across several public English datasets to identify key differences between fake and legitimate news. We assess the detection performance of these features using various traditional classifiers, including single and ensemble methods and analyze how feature reduction affects classifier performance. Our results show that, while traditional classifiers may not fully match transformer-based models, they achieve competitive results with significantly lower computational requirements. We also provide an interpretability analysis highlighting the most influential features in classification decisions. This study demonstrates the potential of interpretable features to build efficient, explainable, and accessible fake news detection systems.
- 4 October 2024
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 8 (10) , 129
Open AccessExploiting Content Characteristics for Explainable Detection of Fake News
The proliferation of fake news threatens the integrity of information ecosystems, creating a pressing need for effective and interpretable detection mechanisms. Recent advances in machine learning, particularly with transformer-based models, offer promising solutions due to their superior ability to analyze complex language patterns. However, the practical implementation of these solutions often presents challenges due to their high computational costs and limited interpretability. In this work, we explore using content-based features to enhance the explainability and effectiveness of fake news detection. We propose a comprehensive feature framework encompassing characteristics related to linguistic, affective, cognitive, social, and contextual processes. This framework is evaluated across several public English datasets to identify key differences between fake and legitimate news. We assess the detection performance of these features using various traditional classifiers, including single and ensemble methods and analyze how feature reduction affects classifier performance. Our results show that, while traditional classifiers may not fully match transformer-based models, they achieve competitive results with significantly lower computational requirements. We also provide an interpretability analysis highlighting the most influential features in classification decisions. This study demonstrates the potential of interpretable features to build efficient, explainable, and accessible fake news detection systems.
- Open Access
- 26 October 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (21) , 11695
Detection of the Severity Level of Depression Signs in Text Combining a Feature-Based Framework with Distributional Representations
Depression is a common and debilitating mental illness affecting millions of individuals, diminishing their quality of life and overall well-being. The increasing prevalence of mental health disorders has underscored the need for innovative approaches to detect and address depression. In this context, text analysis has emerged as a promising avenue. Novel solutions for text-based depression detection commonly rely on deep neural networks or transformer-based models. Although these approaches have yielded impressive results, they often come with inherent limitations, such as substantial computational requirements or a lack of interpretability. This work aims to bridge the gap between substantial performance and practicality in the detection of depression signs within digital content. To this end, we introduce a comprehensive feature framework that integrates linguistic signals, emotional expressions, and cognitive patterns. The combination of this framework with distributional representations contributes to fostering the understanding of language patterns indicative of depression and provides a deeper grasp of contextual nuances. We exploit this combination using traditional machine learning methods in an effort to yield substantial performance without compromising interpretability and computational efficiency. The performance and generalizability of our approach have been assessed through experimentation using multiple publicly available English datasets. The results demonstrate that our method yields throughput on par with more complex and resource-intensive solutions, achieving F1-scores above 70%. This accomplishment is notable, as the proposed method simultaneously preserves the virtues of simplicity, interpretability, and reduced computational overhead. In summary, the findings of this research contribute to the field by offering an accessible and scalable solution for the detection of depression in real-world scenarios.
- 26 October 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (21) , 11695
Open AccessDetection of the Severity Level of Depression Signs in Text Combining a Feature-Based Framework with Distributional Representations
Depression is a common and debilitating mental illness affecting millions of individuals, diminishing their quality of life and overall well-being. The increasing prevalence of mental health disorders has underscored the need for innovative approaches to detect and address depression. In this context, text analysis has emerged as a promising avenue. Novel solutions for text-based depression detection commonly rely on deep neural networks or transformer-based models. Although these approaches have yielded impressive results, they often come with inherent limitations, such as substantial computational requirements or a lack of interpretability. This work aims to bridge the gap between substantial performance and practicality in the detection of depression signs within digital content. To this end, we introduce a comprehensive feature framework that integrates linguistic signals, emotional expressions, and cognitive patterns. The combination of this framework with distributional representations contributes to fostering the understanding of language patterns indicative of depression and provides a deeper grasp of contextual nuances. We exploit this combination using traditional machine learning methods in an effort to yield substantial performance without compromising interpretability and computational efficiency. The performance and generalizability of our approach have been assessed through experimentation using multiple publicly available English datasets. The results demonstrate that our method yields throughput on par with more complex and resource-intensive solutions, achieving F1-scores above 70%. This accomplishment is notable, as the proposed method simultaneously preserves the virtues of simplicity, interpretability, and reduced computational overhead. In summary, the findings of this research contribute to the field by offering an accessible and scalable solution for the detection of depression in real-world scenarios.
- Open Access
- 26 August 2022
- Published by Elsevier in Information Processing & Management
- Vol. 59 (6)
Prediction of stress levels in the workplace using surrounding stress
- 26 August 2022
- Published by Elsevier in Information Processing & Management
- Vol. 59 (6)
Open AccessPrediction of stress levels in the workplace using surrounding stress
- Open Access
- 1 July 2022
- Published by Elsevier in Information Processing & Management
- Vol. 59 (5)
A text classification approach to detect psychological stress combining a lexicon-based feature framework with distributional representations
- 1 July 2022
- Published by Elsevier in Information Processing & Management
- Vol. 59 (5)
Open AccessA text classification approach to detect psychological stress combining a lexicon-based feature framework with distributional representations
- Open Access
- 20 January 2022
- Published by MDPI AG in Electronics
- Vol. 11 (3) , 326
Semantic Modeling of a VLC-Enabled Task Automation Platform for Smart Offices
The evolution of ambient intelligence has introduced a range of new opportunities to improve people’s well-being. One of these opportunities is the use of these technologies to enhance workplaces and improve employees’ comfort and productivity. However, these technologies often entail two major challenges: the requirement for fast and reliable data transmission between the vast number of devices connected simultaneously, and the interoperability between these devices. Conventional communication technologies present some drawbacks in these kinds of systems, such as lower data rates and electromagnetic interference, which have prompted research into new wireless communication technologies. One of these technologies is visible light communication (VLC), which uses existing light in an environment to transmit data. Its characteristics make it an up-and-coming technology for IoT services but also aggravate the interoperability challenge. To facilitate the continuous communication of the enormous amount of heterogeneous data generated, highly agile data models are required. The semantic approach tackles this problem by switching from ad hoc application-centric representation models and formats to a formal definition of concepts and relationships. This paper aims to advance the state of the art by proposing a semantic vocabulary for an intelligent automation platform with VLC enabled, which benefits from the advantages of VLC while ensuring the scalability and interoperability of all system components. Thus, the main contributions of this work are threefold: (i) the design and definition of a semantic model for an automation platform; (ii) the development of a prototype automation platform based on a VLC-based communication system; and (iii) the integration and validation of the proposed semantic model in the VLC-based automation platform.
- 20 January 2022
- Published by MDPI AG in Electronics
- Vol. 11 (3) , 326
Open AccessSemantic Modeling of a VLC-Enabled Task Automation Platform for Smart Offices
The evolution of ambient intelligence has introduced a range of new opportunities to improve people’s well-being. One of these opportunities is the use of these technologies to enhance workplaces and improve employees’ comfort and productivity. However, these technologies often entail two major challenges: the requirement for fast and reliable data transmission between the vast number of devices connected simultaneously, and the interoperability between these devices. Conventional communication technologies present some drawbacks in these kinds of systems, such as lower data rates and electromagnetic interference, which have prompted research into new wireless communication technologies. One of these technologies is visible light communication (VLC), which uses existing light in an environment to transmit data. Its characteristics make it an up-and-coming technology for IoT services but also aggravate the interoperability challenge. To facilitate the continuous communication of the enormous amount of heterogeneous data generated, highly agile data models are required. The semantic approach tackles this problem by switching from ad hoc application-centric representation models and formats to a formal definition of concepts and relationships. This paper aims to advance the state of the art by proposing a semantic vocabulary for an intelligent automation platform with VLC enabled, which benefits from the advantages of VLC while ensuring the scalability and interoperability of all system components. Thus, the main contributions of this work are threefold: (i) the design and definition of a semantic model for an automation platform; (ii) the development of a prototype automation platform based on a VLC-based communication system; and (iii) the integration and validation of the proposed semantic model in the VLC-based automation platform.