Text-Mining & Link-Analysis Workshop
[TextLink 2003]

The workshop aims to focus the intersection of the two increasingly important areas of research: Text-Mining and Link-Analysis. Call for papers (closed) was open until April 21.

Many areas of application involve both unstructured data resources, like textual documents, and a link based organization of these resources, which itself may appear quite obscure and unstructured from the user point of view. On the other hand, text mining and link analysis have evolved as more or less independent research areas, each covering a vast number of scenarios, methods, and techniques. The two appear similar in their requirements for sophisticated analyses and effective techniques to extract and utilize information hidden in the data resource or a network of data.

Although, in practice, these two areas are very much related there have been almost no events so far addressing explicitly the common problems and techniques. Therefore, the aim of this Workshop is to attract the scientists in the two research areas and provide a forum for sharing ideas and exchanging insights from the two fields. This will potentially lead to interesting new ideas and move the research forward.

Over the past five years, Text-Mining has been receiving a growing attention mainly because of the availability of large text corpora in the electronic form and an evident lack of "intelligent" tools and techniques to process that data. Indeed, there is a need for effective and efficient methods for information extraction, text categorization, ontology building, visualization, intelligent search, etc.

Link-Analysis, on the other hand, has been developed over the past 20 years in various fields, including Mathematics (Graph-Theory), Social Sciences (Social-Network-Analysis), and Computer-Science (graph as a data-structure). Recently this area has attracted a wider attention for its applicability in law enforcement investigations (e.g., terrorism), fraud detection (e.g., insurance, banking), WWW analysis (e.g., search engines, marketing), telecommunications (e.g., routers, traffic, connectivity), and similar.

Particularly interesting are the problems and issues that fall within the intersection of the two fields. Typical examples are in the areas of trend analysis, community identification, web user profiling, media clipping, marketing, etc., where link analysis and text analysis complement each other to achieve the effect of higher information utilization. Another interesting scenario is extraction of information from unstructured data, its representation in the graphical form, and further analysis of the graph structure to derive and discover new knowledge. The broader context of the workshop can be related in some respect to
the areas of Data Mining, Machine Learning, Information Retrieval, Natural-Language-Processing, Social Networks Analysis and general Graph Theory.

Particular topics of interest for the workshop include but are not limited to:

• Text Mining
• Link Analysis
• Web Mining
• Information Extraction
• Scalability of developed approaches
• Visualization of text and link structures
• Performance evaluation measures
• Innovative applications

Workshop schedule

• Qing Lu and Lise Getoor, Link-based Text Classification
• Jennifer Neville, Micah Adler and David Jensen, Clustering Relational Data Using Attribute and Link Information
• Anna Goldenberg and Andrew Moore, Empirical Bayes Screening for Link Analysis
• Jeremy Kubica, Andrew Moore, David Cohn and Jeff Schneider, cGraph: A Fast Graph-Based Method for Link Analysis and Queries
• Nicolas Turenne, Learning Semantic Classes for improving Email Classification
• Olivier de Vel, Augmented Sequence Spectrum Kernels for Semi-Structured Document Categorization
• Brian D. Davison, Unifying Text and Link Analysis (short paper)
• Discussion

Note: Participants are expected to register for the main IJCAI conference in addition to the workshop.

Organizing Committee

Marko Grobelnik
J. Stefan Institute, Jamova 39, 1000 Ljubljana, Slovenia 
Marko.Grobelnik@ijs.si
 
Natasa Milic-Frayling
Microsoft Research Ltd, 7 J J Thomson Avenue, Cambridge, CB3 0FB, United Kingdom 
natasamf@microsoft.com

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

Past events

We feel that the continuity of meeting and exchanging ideas is essential for effective promotion and development of this research area.

• ICML-1999 Workshop on Machine Learning in Text Data Analysis (TextML-1999)
• KDD-2000 Workshop on Text Mining (TextKDD'2000 )
• ICDM-2001 Workshop on Text Mining (TextDM'2001)
• ICML-2002 Workshop on Text Learning (TextML-2002)

This Workshop is partially supported by the European FP5 project "Data Mining and Decision Support for Business Competitiveness: A European Virtual Enterprise (Sol-Eu-Net)".