16px-feed-icon Events Diese Seite auf deutsch anzeigen

TMS - Text Mining Services

Conference, 2009-03-23 – 2009-03-25
Mediencampus, Leipzig, Germany

A necessary precondition for High Tech Services is a systematic and structured acquisition, generation, processing, administration, presentation, reuse, and publication of contents. Content services make available the resources and programs needed for that. Public digital text and data resources are linked together and made accessible by common standards. New software architectures integrate digital resources and processing tools like text and data mining to develop new and better content for specific applications.

Text and content mining is of central importance for internet based media services and intelligent search services. These services will be standard for next generation portals. They also form the basis of the so-called E-Humanities. Text Mining services already are of commercial interest for the media and publishing houses, for on-line and off-line journalism, quality analysis and assurance in industries, patent and technology mining, trend mining and trend management, and media and marketing analysis.

The workshop will address and discuss urging research issues and approaches for text mining services as part of the SABRE multi conference focusing on services science in cooperation with the Department of Computer Science and the Information Systems Institute as well as the Historisches Seminar of the University of Leipzig, University of Applied Science Leipzig and the Leipzig Graduate School of Managment, together with the German government funded research projects eAQUA (, D-SPIN (, Topic Maps 2.0 Lab (, and the EU funded project CLARIN ( The up-to-date state of the art in text mining services will be presented and discussed amongst representatives both from research and industry as well as different scientific disciplines.

Conference Program

Monday, March 23rd

Workshop Sentiment Analysis

  • Sentiment in German-language News and Blogs, and the DAX
    Robert Remus (University of Leipzig), Khurshid Ahmad (Trinity College, Dublin), Gerhard Heyer (University of Leipzig)

  • Feature Difference Quantity: Classification Using Feature Distribution
    Alexander Mehler (University of Frankfurt), Ulli Waltinger (University of Bielefeld)

  • Correlating Market movements with consumer confidence and sentiments: A longitudinal study
    Nicholas Daly (Trinity College, Dublin), Khurshid Ahmad (Trinity College, Dublin), Colm Kearny (Trinity College, Dublin)

  • How to Design Textmining Services for Marketing Research Applications
    Daniel Wagenführer (University of Hamburg)

Tuesday, March 24th

Keynote SABRE
Martin Jetter (IBM Germany)

Relation Extraction based on Unsupervised Syntactic Parsing
Martin Schierle (Daimler AG), Christian Haenig (Daimler AG)

Entity Resolution by Kernel Methods
Anja Pilz (Fraunhofer IAIS St. Augustin), Lukas Molzberger (Fraunhofer IAIS St. Augustin), Gerhard Paaß (Fraunhofer IAIS St. Augustin)

DI.ANA: A digital intelligence service to support strategic decisions based on textual data – A report on 5 years of development and application experience at a global OEM
Peter Walde (Volkswagen AG)

Structured Knowledge for Low-Resource Languages: The Latin and Ancient Greek Dependency Treebanks
David Bamman (The Perseus Project, Tufts University), Gregory Crane (The Perseus Project, Tufts University)

Word Lists, Concordances, Text Comparison, and Morphology in Latin and Ancient Greek Texts
Robert Maier (eAqua Project)

Language Resources, Taxonomies and Metadata
Erhard Hinrichs (University of Tuebingen), Lothar Lemnitzer, (University of Tuebingen), Andreas Witt (University of Tuebingen)

A prototype infrastructure for DSpin-services based on an flexible XML data interchange format
Volker Boehlke (University of Leipzig, D-SPIN Project)

Wednesday, March 25th

Text Mining – Creating Semantics in the real world
Stefan Wrobel (Fraunhofer IAIS, St. Augustin)

Automatic Extraction of Topic Maps based Argumentation Trails
Lutz Maicher (University of Leipzig, Topic Maps Lab), Marco Büchler (University of Leipzig, eAqua Project), Benjamin Bock (University of Leipzig, Topic Maps Lab)

Applying Domain Knowledge from Structured Citation Formats to Text and Data Mining: Examples Using the CITE Architecture
Gabriel Weaver (Dartmouth Computer Science Department), Neel Smith (College of the Holy Cross)

Realising interoperability for digital Classics resources
Tobias Blanke (King’s College London), Mark Hedges (King’s College London), Gabriel Bodard (King’s College London)

TextGrid – Research Infrastructure for the e-Humanities
Martina Kerzel (Göttingen State and Universtity Library), Heike Neuroth (Göttingen State and Universtity Library), Jens Mittelbach (Göttingen State and Universtity Library)

LLS – A 4 Years Summary of Providing Linguistic Web Services
Marco Büchler (University of Leipzig, eAqua Project), Gerhard Heyer (University of Leipzig)

Discussion Panel
The key points of each TMS session will be summarized and evaluated by the session chairpersons. The panel will attempt to deliver an overview of some of the key issues in text mining services, solutions and approaches presented during the conference, and open questions remaining.
Chair: Gerhard Heyer (University of Leipzig)

Contact: Prof. Dr. Gerhard Heyer, Sven Windisch

other link icon Further informations