Projects

      Information Retrieval Group (IRG@UAM), UAM

• Interventions towards Fair Information Access Systems (IFIAS)
  National project (PID2022-139131NB-I00), Ministerio de Ciencia e Innovación, Plan Nacional I+D+i, September 2023 - August 2026
  Information retrieval, recommender systems, fairness, transparency, explicability, biases, opinion mining, argument mining, social network analysis.
• Beyond static recommendation: fairness, interaction and transparency (FIT)
  National project (PID2019-108965GB-I00), Ministerio de Ciencia e Innovación, Plan Nacional I+D+i, June 2020 - May 2023
  Sesgos en recomendación, recomendación interactiva, explicación de recomendaciones, sistemas de recomendación conversacionales.
• Digital participatory democracy through efficient intruments and models for Open Government in Andalusian local governmets
  Regional project (PRY137/19), Fundación Centro de Estudios Andaluces - XI Convocatoria de Proyectos de Investigación, May 2020 - May 2022
  Conversational systems for e-participation.
• Amermad. América en Madrid - Patrimonios Interconectados e Impacto Turístico en la Comunidad de Madrid
  Regional project (H2019/HUM-5694), Comunidad Autónoma de Madrid. Programa de actividades de I+D entre grupos de investigación de la Comunidad de Madrid en Ciencias Sociales y Humanidades 2019, January 2020 - December 2022
  Knowledge modeling and recommender systems in interconnected cultural heritage domains.
• Lowcomote. Training the Next Generation of Experts in Scalable Low-Code Engineering Platforms
  European project (813884), Program H2020. Innovative Training Networks (ITN) 2018, January 2019 - December 2022
  Recommender systems for software and modeling engineering tasks.
• Recommendation in social media
  National project (TIN2016-80630-P), Ministerio de Economía y Competitividad, Plan Nacional I+D+i, January 2017 - December 2019
  Recommendation in social media: Context, diversity and algorithmic bias.
• GICE
  National project (RTC-2014-2089-7), October 2014 - September 2017
  Development of an Intelligent Gamification Platform for E-commerce. Project with BrainSINS, Offerum, Interactiv4 and Jugo.
  
• Voxpopuli
  National project (TIN2013-47090-C3-2), January 2014 - December 2015
  Efficient reputation analysis, propagation and recommendation in social network environments. Coordinated project with UNED (coordinator) and University of A Coruña.
• Predict
  National project (TIN2011-28538-C02), January 2012 - December 2013
  The Predict project addresses the extension of information access technologies towards the incorporation of new dimensions, namely novelty and diversity, subjectivity, context, and time, as essential aspects of information access effectiveness and tasks that are not captured in traditional Information Retrieval (IR) paradigms and models, in order to enhance the quality, effectiveness, and user satisfaction with retrieval systems, in further ways than state of the art technologies and theories in the field currently procure. The research focuses on these problems within the specific scope of personalized Information Retrieval and Recommender Systems.
• ReSHeT: Recommender Systems in the Social Web: Heterogeneity and Time Dimension
  Regional project (CCG10-UAM/TIC-5877), January 2011 - December 2011
  The ReSHeT project addresses two improvements in Recommender Systems for the Social Web: the consideration of information heterogeneity and the inclusion of the time dimension. Specifically, it proposes the development of recommendation models that make use of user preferences from several sources (ratings, annotations, and resource consumptions, social networks, etc.), and can be applied to resources belonging to different media (text, image, audio, video). By testing these models on a dataset obtained from a real social system, we shall analyse factors that are influenced by time (e.g. changes in user preferences, differences among the user's preferences according to the time of day or the month of the year, resources subject to fashions and trends, etc.). Based on such analysis, we shall propose and evaluate a strategy to change or adjust the developed recommendation models over time.
• MA2VICMR: Mejorando el acceso, el análisis y la visibilidad de la información y los contenidos multilingües y multimedia en red para la Comunidad de Madrid
  National project (S2009TIC-1542), January 2010 - December 2013
  The MAVIR Consortium is a research network co-funded by the Community of Madrid under the 4th Regional Plan for Scientific Research and Technological Innovation (IV PRICIT). It is formed by a multidisciplinary team of scientists, technicians, linguists and archivists to develop an integration effort in research, training and technology transfer. The research lines that are developed by MAVIR members belong to Natural Language Technologies and Scientific Communication through the Web.

      Networked Semantics Team (NETS), UAM

• RIM3. Information Retrieval on different media based on multidimensional models: relevance, novelty, personalization and context
  National project (TIN-2008-06566-C04-02), January 2009 - December 2011
  This project tackles the IR problem from a multidimensional perspective. Besides the dimension of relevance, systems could be endowed with advanced capabilities for novelty detection, redundancy filtering, subtopic detection, personalization and context-based retrieval.
• i3media
  National project (CENIT-2007-1012), January 2007 - December 2010
  Technologies for Automated Intelligent Audiovisual Content Creation and Management.
• Spanish Network of Semantic Web
  National project (TSI-2006-26928-E), November 2006 - September 2008
  The Spanish Network of Semantic Web aims to ease the interchange the exchange and transfer of knowledge concerning ontologies and the Semantic Web between national research groups.
• MESH: Multimedia sEmantic Syndication for enHanced news services
  EU/FP6 Integrated Project (FP6-027685), March 2006 - February 2009
  MESH applies multimedia analysis and reasoning tools, network agents and content management techniques to extract, compare and combine meaning from multiple multimedia sources, and produce advanced personalized multimedia summaries, deeply linked among them and to the original sources to provide end users with an easy-to-use "multimedia mesh" concept, with enhanced navigation aids. A step further is to empower users with the means to reuse available content by offering media enrichment and semantic mixing of both personal and network content, as well as automatic creation from semantic descriptions.
• S5T. Scaleable semantic personalised search of spoken and written contents on the Semantic Web
  National project (TIN-2005-06885), December 2005 - November 2008
  This project provides a) the development of a novel semantic search model, with ontology-based content ranking algorithms; b) the combination of personalisation techniques with the semantic-based representation models, to achieve improvements in the relative precision and relevance of search results with respect to the particular interests of individual users; c) the integration of text and voice contents in a single access platform for large-scale repositories; and d) an experience in the realisation the of Semantic Web proposals.
• aceMedia. Integrating Knowledge, Semantics and Content for User-centred Intelligent Media Services
  EU/FP6 Integrated Project (FP6-001765), January 2004 - December 2007
  The main technological objectives of aceMedia project are to discover and exploit knowledge inherent to the content in order to make content more relevant to the user; to automate annotation at all levels; and to add functionality to ease content creation, transmission, search, access, consumption and re-use. In addition, available user and terminal profiles, the extracted semantic content descriptions and advanced mining methods will be used to provide user and network adaptive transmission and terminal optimised rendering.
• Bronto. XBRL Taxonomies and OWL Ontologies for Investment Funds
  National project (FIT-340000-2005-256), August 2005 - July 2006
  The definition of XBRL taxonomies and OWL ontologies for investment funds. The principal aim is to evaluate the use of XBRL vs. the use of OWL in the financial domain, in order to cross-fertilize both research lines and to assess the applicability of both languages to the financial market.

      Machine Learning Group (GAA, Grupo de Aprendizaje Automático), UAM

• AE3. Learning, Evolution and Extreme Statistics
  National project (TIN-2004-07676-C02-01), December 2004 - November 2007
  The overall aim of the "Learning, Evolution and Extreme Statistics" (AE3 in its Spanish initial letters) project is to study those hard pattern recognition problems where objects of interests are statistically overwhelmed by others, in three concrete areas: natural image statistics, extreme sample classification and time modeling in finance. The main techniques to be used are machine learning, computer vision or neurobiological modelling.