---------------------------------------- ----------------------------------------

Conference on Data Mining and Data Warehouses (SiKDD 2006)

October 9, 2006, Ljubljana, Slovenia

---------------------------------------- ----------------------------------------

To be held at 9th International Multi-conference on Information Society IS-2006

Data handling technologies have significantly progressed in the last ten years. The first phases mainly dealing with storing and efficiently accessing the data, resulted in the development of industry delivering tools for handling large databases, standardization of related processes, queering languages, etc. When the data storage was not a primary problem any more the need for improving the database organization resulted in the databases supporting not only transactions but also analytical views of the data. At this point data warehousing with OLAP (On-Line-Analytical-Processing) entered as a usual part of a company information system. The OLAP paradigme stil requires from the user to set well defined questions which is not always easy and possible. This led to the development of Data Mining offering automatic data analysis trying to obtain some new information from the existing data and enabling the user some new insights in the data. Further development of methods for Text Mining enables handling textual data in addition to well structured data in databases. Large amount of data and activities on the Web is further  addressed in Web Mining where in addition to content of the Web documents, the structure of  the Web and Web log-files are analysed.

Conference Themes

----------------------------------------

Instructions for Authors

Authors are invited to contribute papers that present the state-of-the-art, development goals, applications and future trends in the above mentioned areas.

Authors are invited to submit complete papers not exceeding 4 pages, written in English and formatted following IS-2006 formatting instructions. A sample format in Microsoft Word is available at http://is.ijs.si/primer.doc. The authors should submit the papers by August 31, 2006 preferably in Microsoft Word (or alternatively in.pdf) format by e-mail to: Dunja.Mladenic@ijs.si with "Subject: SiKDD 2006 paper submission".

The accepted contributions will be published on this Web page and in the conference proceedings, which will be made available to participants upon registration.

----------------------------------------

Conference Program

Invited talks, presentations of accepted papers and demonstration of developed tools.

9:30 - 11:00 Text Mining and Semantic Web

  Hierarchical text categorization using coding matrices, Janez Brank, Dunja Mladenic, Marko Grobelnik
  Semi-automatic data-driven ontology construction system, Blaz Fortuna, Marko Grobelnik, Dunja Mladenic
  Comparison of ontologies built on titles, abstracts and entire texts of articles, Ingrid Petric, Tanja Urbancic, Bojan Cestnik
  Approximate representation of textual documents in the concept space, Jasminka Dobsa, Bojana Dalbelo Basic
11:00 - 11:30 Coffee break

11:30 – 12:30 Algorithms: Text Mining and Link Analysis

 

  Overview of algorithms for graph drawing, Bostjan Pajntar
  Finding community structure in social network analysis – overview, Jan Rupnik
  Loose phrase string kernels, Janez Brank

12:30 - 14:30 Lunch break

14:30 – 16:00 Applications of Text and Data Mining
  IST World – machine learning and data mining at work, Jure Ferlež
  Extending IST World database with Serbian research publications, Milos Radovanovic, Jure Ferlez, Dunja Mladenic, Marko Grobelnik, Mirjana Ivanovic
  Learning to predict forest fires with different data mining techniques, Daniela Stojanova, Pance Panov, Andrej Kobler, Saso Dzeroski, Katerina Taskova
  Predicting Forest Stand Properties from Satellite Images with Different Data Mining Techniques, Katerina Taškova, Pance Panov, Andrej Kobler, Saso Dzeroski, Daniela Stojanova
16:00 - 16:30 Coffee break
  Proper versus Ad-Hoc MDL Principle for Polynomial Regression, Aleksandar Peckov, Ljupco Todorovski, Saso Dzeroski
  Similarity constraints in beam-search induction of predictive clustering trees, Dragi Kocev, Saso Dzeroski, Jan Struyf
  Fast convergence clustering ensembles, Javad Azimi, S. Reza Davoodi, Morteza Analoui

 ----------------------------------------

Important Dates 

----------------------------------------

Organization

Program Chairs

Marko Grobelnik
J.Stefan Institute, Jamova 39, 1000 Ljubljana, Slovenia
Marko.Grobelnik@ijs.si

Dunja Mladenic
J.Stefan Institute, Jamova 39, 1000 Ljubljana, Slovenia
Dunja.Mladenic@ijs.si
----------------------------------------

Previous events

----------------------------------------

Further information on registration, accommodation etc. is available at http://is.ijs.si, and on telephone +386 1 4773 900, or fax. +386 1 4773131

---------------------------------------- ----------------------------------------