Workshop on Link Analysis and Group Detection (LinkKDD2004) - Call for Papers

August 22, 2004

To be held at KDD-2004, The Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Seattle, WA, USA, 22-25 August 2004

Call for papers on the following topics is open till June 14, 2004.

Below are submission guidelines, attendance information, important dates and organization details.

Workshop Description

The workshop aims to focus on an increasingly important areas of research, Link Analysis and Group Detection.

Link Analysis and Link Discovery has been developed over the past 20 years in various fields including Discrete 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. The common goal of this research is the development of techniques for mining large collections of data to extract valuable knowledge that may be present as hidden patterns or links among seemingly unrelated items. Successful applications will discover the hidden structure of organizations, relate groups, identify fraudulent behavior, model group activity and provide early detection of emerging threats. The departure from standard approaches is made clear in the following typical characteristics of the addressed problems and their representation:

• Data is heterogeneous, arriving from multiple sources. The data and patterns sought include representations of people, organizations, objects, actions and events. Each of these entities has its own set of attributes, and there are many types of relations that might exist between them.
• Unlike conventional data mining, in which nodes are variables and links are statistical relations among variables, nodes represent entities and links are relations amongst entities.
• Approaches assesses the likelihood that an instance of a specific graphtheoretic structure in the data matches a pattern of interest. The structure may include temporal, spatial, organizational, and/or transactional patterns.
• The addressed problems involve estimating a population based on a sample of data. Typically, a relatively low number of observations for each entity can be recorded, and the overall sample is typically small relative to the size of the population.
• The data becomes available over time, so the timing of when to make a decision based on the analysis is a central issue.

Particularly interesting for the workshop are problems and issues that fall within the intersection of Link Analysis and fields such as Web and Text Mining, Relational Data Mining, and more general, Data Mining. Typical examples are in the area of trend analysis, community identification, Web user profiling, media clipping, marketing, etc., where Link Analysis complements other fields of research in order to achieve the higher information utilization. Another interesting scenario is extraction of information from unstructured data, representation of extracted data in the graphical form, and further analysis of the resulting 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 the general Graph Theory.

Topics of interest

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

• Link-Analysis/Graph Mining
• Social Network Analysis and community finding with emphasis on semantic links, small world phenomenon and scale free networks
• Web-Mining and Text-Mining in relation to Link Analysis
• Scalability of developed approaches including discovery in very large databases, connectivity curse, discovering similar entities, noise, corruption and clutter etc.
• Visualization of link structures
• Performance evaluation measures
• Innovative applications related to Link Analysis and Group Discovery including entity databases, temporal database, spatial databases and CRM databases
• Theoretic contributions including related theoretic fields such as graph theory, information theory, natural language processing, agent theory, complex systems, trust models and dynamic pricing models.
• Review and analysis of current integrated system, tools, commercial products, educational and commercial package available in the market.

Submission Guidelines

Submissions should be sent by June 14, 2004, in the electronic form as a PDF or PostScript file to adibi@isi.edu (asking for confirmation) Subject: LinkKDD-2004 workshop submission paper.

Submissions should be max. 10 pages, using the ACM proceedings style (two columns, 9pt font, approx. 1in margins; templates are available). Use the same formating as for the main KDD-2004 conference.

Submitted papers will be reviewed by referees from the Program Committee. Accepted papers will be published in the Workshop proceedings. The authors will be notified about the acceptance or rejection of their papers by June 30, 2004. Camera-ready versions of the papers are due July 7, 2004.

Attendance

Attendance is not limited to the paper authors. We strongly encourage interested researchers from related areas to attend the workshop. The workshop should be of interest to researchers and practitioners conducting research or building applications that involve various data analysis and rich data and knowledge representations, in particular, those from: Academic Data Mining (analytical aspects of dealing with link structures), Commercial Data Mining (new application areas), Social Networks Analysis (algorithmic aspects of dealing with large network structures), Relational Data Mining/Association Rules (alternative representations and dealing with the data), Natural Language Processing/Text Mining (representational aspects). We expect that the workshop topics will attract attention of regular KDD attendees who are interested in Data Mining, Machine Learning, and Natural Language Processing but also potentially encourage the attendance of KDD by participants interested in Social Network Analysis who would otherwise not choose to come to the conference.

Important Dates

Organization

Jafar Adibi
Information Sciences Institute, University of Southern California, 4676 Admiralty Way Suit 1001, Marina del Rey, CA 90292

Hans Chalupsky
Information Sciences Institute, University of Southern California, 4676 Admiralty Way Suit 1001, Marina del Rey, CA 90292

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

Natasa Milic-Frayling
Microsoft Research Ltd, 7 J J Thomson Avenue, Cambridge, CB3 0FB, United Kingdom

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

Program Committee

• Jafar Adibi, University of Southern California, USA
• Lada Adamic, HP Laboratories, Palo Alto, USA
• Sarabjot Anand, University of Ulster, UK
• Janez Brank, J.Stefan Institute, Ljubljana, Slovenia
• Hans Chalupsky, University of Southern California, USA
• Diane Cook, University of Texas at Arlington, Arlington, USA
• Mark Craven, University of Wisconsin, USA
• Gary Flake, Yahoo Research Lab, Pasadena, USA
• Rayid Ghani,Accenture Technology Labs - Research, Chicago, USA
• Marko Grobelnik, J.Stefan Institute, Ljubljana, Slovenia
• David Jensen, University of Massachusetts, USA
• Christopher A. Meek, Microsoft Research, Redmond, WA, USA
• Natasa Milic-Frayling, Microsoft Research Ltd, Cambridge, UK
• Dunja Mladenic, J.Stefan Institute, Ljubljana, Slovenia
• Andrew Moore, Carnegie Mellon University, Pittsburgh, USA
• Ion Muslea, SRI International, Menlo Park, USA
• Jeff Schnieder, Carnegie Mellon University, Pittsburgh, USA
• John Shawe-Taylor, University of Southampton, UK
• Sean Slattery, Applied Psychology Research, London, UK

Past events

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

• ICML-99 Workshop on Machine Learning in Text Data Analysis
• KDD-2000 Workshop on Text Mining
• ICDM-2001 Workshop on Text Mining
• ICML-2002 Workshop on Text Learning
• IJCAI-2003 Workshop on Text-Mining and Link-Analysis
• KDD-2003 Workshop on Link Analysis for Detecting Complex Behavior