Overview

It has been premised by many that interactive data mining techniques that aptly integrate human intuition, visual pattern recognition, and background knowledge with the number crunching capabilities of modern computers—by means of visualization and feedback loops—could help researchers, businesses, journalists, and other data users gain insights unattainable otherwise. Yet, the development of methods and techniques that can function as building blocks for such interac- tive systems is still in its infancy.

The goal of the IDEA workshop is to encourage the development of methods and techniques to (1) more effectively and efficiently communicate results from analysis algorithms, e.g., visualization of patterns and models, (2) enable rich, efficient, and accurate user feedback to select and manipulate models or provide information about their relevance or interestingness, (3) provide data analysis at interactive speed. We aim to raise awareness of the need for data analysis algorithms that enable interactive use (take feedback into account), so the algorithms and the user work together to make discoveries in complex data. This hybrid approach—combining powerful techniques from data mining, visualization, and HCI—forms an new class of techniques that enable truly inter-active data analysis. The focus and emphasis is on interactivity and communication—information transfer to and from users, i.e., techniques at the interface of data mining, visualization, and HCI. In other words, we intend to explore how the best of these different but related domains can be combined such that the sum is greater than the parts.

Topics of interests for the workshop include, but are not limited to:
-Data mining (DM)
-Human-computer interaction (HCI)
-Visualization (VIS)

We invite any type of contribution on these topics: new principles, methods, systems, empirical evaluations, etc.