Text mining.

Text mining or text analytics is the area that brings together techniques to extract structured information or knowledge from texts. These techniques allow people to analyse information coded in text collections (on occasions of the big data type) effectively and easily, and this considerably facilitates decision-making processes. There are all kinds of tasks within this broad area: text classification, text clustering, named entity extraction, opinion extraction, document summarization and information retrieval, among others. Today, text mining technologies are being successfully used to address a whole range of needs of governments, research and markets.

Main lines of research

  • Cross-language information retrieval
  • Language identification
  • Opinion mining
  • Topic labeling
  • Storyline generation

Ongoing research projects

  • VIGICOVID: Vigilancia automatizada de cuestiones clave sobre la COVD19 en publicaciones científicas. Fondo Supera COVID-19 (2020-2021).
  • COGNOSCERE: Inteligencia y análitica avanzada multidominio basada en Big Data y Deep Learning. Cofunded by the Spanish Government (Ministerio de Asuntos Económicos y Transformación Digital, Impulso a las Tecnologías Habilitadoras Digitales - TSI-100905-2019-15, 2019-2021) ministerio de asuntos económicos y transformación digital
  • GEPSA: Gizarte-Erronkei erantzun eta Politika Eraginkorrak diseinatzeko prentsaren azterketa Semantikoan oinarritutako tresna Adimenduna. Hazitek Program, Basque Government (2019-2020)
  • HitZain: Plataforma de vigilancia en medios para seguimiento competitivo de mercado. Hazitek Program, Basque Government (2016-2018)