Pasar al contenido principal

MODELOS PARA LA REPRESENTACION Y EL ANALISIS DE INFORMACION COMPLEJA EN REDES Y GRAFOS CON INCERTIDUMBRE

PID2024-155289NB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para la Investigación y el Desarrollo Experimental
Subprograma Subprograma Estatal de Generación de Conocimiento Científico-Técnico y Desarrollo Experimental
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2024
Plan Estatal 2024-2027 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD COMPLUTENSE DE MADRID

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Redes sociales y desigualdad, rich-clubs y sentimientos en Twitter durante el debate sobre las macro-granjas españolas, Social networks and inequality, Redes sociais e desigualdade

  • Casas-Mas, Belén|||0000-0001-8329-0856
  • Gómez González, Daniel|||0000-0001-9548-5781
  • Simon de Blas, C.|||0000-0002-6963-1295
A finales de diciembre de 2021 el ministro de Consumo en España realizó unas declaraciones al diario The Guardian que provocaron un debate encendido en las redes sociales sobre las macro granjas españolas. En este artículo se aborda el análisis de los mensajes de Twitter en torno a este fenómeno que derivó en debates cooptados por los líderes políticos, quienes centralizaban la opinión pública. La base de datos se compone de 339.901 mensajes descargados en la red durante dos semanas del mes de enero de 2022. Los mensajes se han analizado aplicando técnicas de «Social Network Analysis»: algoritmos machine learning y diccionarios de análisis de sentimiento para indagar sobre los niveles de negatividad que presentan los mensajes publicados. Los principales resultados apuntan a estrategias de comulación elitistas y poco inclusivas en algunos de los partidos y otras más igualitarias, con temáticas que se centran principalmente en la protección de "los ganaderos" frente a la cuestión de la emergencia climática., In December 2021, the Spanish Minister of Consumer Affairs made statements to the newspaper The Guardian that sparked a heated debate on social networks about Spanish macro farms. This article addresses the analysis of Twitter messages regarding this phenomenon that led to debates co-opted by political leaders, who centralized public opinion. The database is made up of 339,901 messages downloaded on the network during two weeks in January 2022. The messages have been analyzed using "Social Network Analysis" techniques: machine learning algorithms and sentiment analysis dictionaries to investigate the levels of negativity presented by the published messages. The main results point to elitist and non-inclusive communication strategies in some of the parties and others that are more egalitarian, with themes that focus mainly on the protection of "livestock farmers" against the issue of the climate emergency., No final de dezembro de 2021, o Ministro do Consumidor da Espanha fez declarações ao jornal The Guardian que geraram um debate acalorado nas redes sociais sobre as mega fazendas espanholas. Este artigo analisa mensagens do Twitter sobre esse fenômeno, que levaram a debates cooptados por líderes políticos, que centralizaram a opinião pública. O banco de dados consiste em 339.901 mensagens baixadas da rede durante duas semanas em janeiro de 2022. As mensagens foram analisadas usando técnicas de Análise de Redes Sociais: algoritmos de aprendizado de máquina e dicionários de análise de sentimento para investigar os níveis de negatividade apresentados pelas mensagens publicadas. Os principais resultados apontam para estratégias de campanha elitistas e não inclusivas em alguns partidos, enquanto outros são mais igualitários, com temas que focam principalmente na proteção dos "pecuaristas" da emergência climática.
Repositori Institucional UIB
Publicación Artículo científico (JournalArticle)

On Modularity, Indistinguishability and Generalized Metrics: Duality and Aggregation

  • Jaume-Martin, Gabriel
  • Talavera, Francisco Javier
  • Elorza, Jorge
  • Valero, Oscar
[eng] In this paper, we prove that, on the one hand, a duality relationship between different types of modular T-transitive relations and the reciprocal modular generalized metrics exists and, on the other hand, that, based on this duality, a construction of functions that aggregate modular T-transitive relations can be made from functions aggregating generalized metrics. Furthermore, we provide a guide for the families of that type of functions that can be used for the aforementioned purpose. Finally, illustrative examples of how to create such functions via the duality are given.
Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Publicación Artículo científico (JournalArticle)

The functional Choquet integral

  • Bustince Sola, Humberto
  • García-Zamora, Diego
  • Ferreira, Eva
  • Montes Rodríguez, Susana
  • Montero, Javier
  • Pereira Dimuro, Graçaliz
  • Miguel Turullols, Laura de
  • Fernández Fernández, Francisco Javier
  • Santiago, Regivan
  • Roldán López de Hierro, Antonio Francisco
We introduce the notion of functional Choquet integral (FCI), a new family of fusion operators that are aggregation functions in many cases, obtained by replacing the capacity values in the discrete Choquet integral with data-dependent fusion functions applied to the ordered tail of the input vector. Unlike previous extensions, different functions are allowed at each summation term, providing additional modeling flexibility while preserving the ordered-difference structure of the Choquet integral. We provide a detailed mathematical analysis of the main structural properties of the FCI. Necessary and sufficient conditions are established for idempotency, homogeneity, monotonicity, and shift-invariance. In particular, we prove that monotonicity of the FCI is guaranteed under a double-increasing condition on the generating vector of functions, and a sufficient condition is given for comonotone additivity. These results clarify both the expressive power and the structural limitations of the proposed framework., This work has been partially supported by Grants C-EXP-153-UGR23 and P24_00565 funded by Consejería de Universidad, Investigación e Innovación, by ERDF Andalusia Program 2021-2027; by Grant PID2024-157156OB-I00 funded by MCIN/AEI/10.13039/501100011033/ERDF UE; by the research project PID2025-168223NB-I00, funded by MCIN/AEI/10.13039/501100011033/ERDF UE; and by the research Project PID2024-155289NB-I00 funded by MICIU/AEI/10.13039/501100011033 and ERDF/EU. Regivan Santiago is supported by the Conselho Nacional de Desenvolvimento Científico e Tecnológico -CNPq/Brazil (Proc. 403748/2024-0 and 306893/ 2025-8). Graçaliz Pereira Dimuro is supported by CNPq/Brazil (Proc. 304118/2023-0, 407206/2023-0) and FAPERGS/Brazil (23/2551-0001865). Additional support was provided by Project PID2022-139886NB-I00 funded by MCIN/AEI/10.13039/ 501100011033; by Project SEK-25-GRU-GIC-24-018 funded by the Government of the Principality of Asturias (Principado de Asturias); and by the European Union under Grant Agreement No. 101132914 (AI4RA). Open access funding provided by Universidad Pública de Navarra.
Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Publicación Artículo científico (JournalArticle)

CRB-NCE: an adaptable cohesion rule-based approach to number of clusters estimation

  • Tinguaro Rodríguez González, Juan
  • González García, Xabier
  • Gómez, Daniel
  • Bustince Sola, Humberto
Accurate number-of-clusters estimation (NCE) is a central task in many clustering applications, particularly for prototype-based k-centers methods like k-Means, which require the number of clusters k to be specified in advance. This paper presents CRB-NCE, a general cluster cohesion rule-based framework for NCE integrating three main innovations: (i) the introduction of tail ratios to reliably identify decelerations in sequences of cohesion measures, (ii) a threshold-based rule system supporting accurate NCE, and (iii) an optimization-driven approach to learn these thresholds from synthetic datasets with controlled clustering complexity. Two cohesion measures are considered: inertia (SSE) and a new, scale-invariant metric called the mean coverage index. CRB-NCE is mainly applied to derive general-purpose NCE methods, but, most importantly, it also provides an adaptable framework that enables producing specialized procedures with enhanced performance under specific conditions, such as particular clustering algorithms or overlapping cluster structures. Extensive evaluations on synthetic Gaussian datasets (both standard and high-dimensional), clustering benchmarks, and real-world datasets show that CRB-NCE methods consistently achieve robust and competitive NCE performance with efficient runtimes compared to a broad baseline of internal clustering validity indices and other NCE methods., This work has been supported by projects PID2021-122905NB-C21, PID2022-136627NB-I00 and PID2024-155289NB-I00 of the Government of Spain.