• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Book

CDUD 2012 - Concept Discovery in Unstructured Data

Academic editor: S. Kuznetsov, D. I. Ignatov, J. Poelmans.
Concept discovery is a subarea of Knowledge Discovery in Databases (KDD) where concept models, such as Formal Concept Analysis (FCA), multimodal clustering, conceptual graphs and other, are used for gaining insight into the underlying conceptual structure of data. Traditional machine learning techniques are mainly focusing on structured data given by object-attribute tables, whereas most data available nowadays are given in unstructured, often textual, form. As compared to traditional data mining techniques, human-centered instruments of concept discovery actively engage domain experts in the discovery process. This volume contains the papers presented at the 2nd International Workshop on Concept Discovery in Unstructured Data (CDUD 2012) held on May 10, 2012 at the Katholieke Universiteit Leuven, Belgium. This workshop welcomes papers describing innovative research on data discovery in complex data. Moreover, this workshop provides a forum for researchers and developers of data mining instruments, working on issues associated with analyzing unstructured data. This year the committee decided to accept 11 papers for publication in the proceedings. Each submission was reviewed by on average 3 program committee members. A. Mestrovic presents an application of concept lattices to semantic matching in Croatian language. A. Chepovskiy et al. propose a method for automatic language identi cation for transliterated texts. X. Naidenova describes a novel neural network based data structure for inferring classi cation tests. A. Kravchenko et al. introduce an approach for expert search which is based on analyzing e-mail communication patterns. D. Ustalov et al. propose an ontologybased approach for text-to-picture synthesis. A. Skabin presents a computerized recognition system for hand-written historical manuscripts. A. Panchenko et al. extract semantic relations between concepts from Wikipedia using KNN algorithms. D. Fedyanin uses parameter identi cation methods for Markov models and applies them to influence analysis in social networks. S. Milyaev et al. discuss a new method for self-tuning semantic image segmentation. A. Vorobev proposes a probabilistic model for evaluating the quality level of projects, authors and experts in collaborative innovation platforms. D. Gnatyshak et al. present a novel pseudo-triclustering algorithm and applied it to online social network data. A. Bozhenyuk et al. discuss methods for maximum flow and minimum cost flow fi nding in fuzzy setting. We would like to express our gratitude to all contributing authors and reviewers. We also want to thank our sponsors Amsterdam-Amstelland police, IBM Belgium, Research Foundation Flanders, Vlerick Management School, OpenConnect Systems and Higher School of Economics (Moscow, Russia). Finally, we should thank the authors of the EasyChair system which helped us to manage the reviewing process.     May 10, 2012 Leuven Dmitry I. Ignatov Sergei O. Kuznetsov Jonas Poelmans  
Chapters
CDUD 2012 - Concept Discovery in Unstructured Data