Attribute based redescription set exploration

Functionality

The attribute based exploration uses the cross-view attribute coocurence heatmap to display which attributes occur often together in redescription queries. The exploration process can be done in several steps:

1. Select the order which will be used to arrange the attributes in a heatmap
2. Select the attribute pair of interest (different attributes can be loaded by using pages at the bottom of heatmap)
3. Scroll through redescription table and select some interesting redescription
4. Examine additional information about the selected redescription

Clicking on some of the components displays new elements on the page. The elements are placed below currently displayed components, so depending on the screen size, you might need to scroll to use them.

This exploration technique is demonstrated on the DBLP dataset . This dataset contains 6455 entities (authors of scientific papers) described by two views containing Boolean attributes without missing values. The first view contains 304 descriptors describing which author published papers on which conferences. The second view contains information about co-authorships between 6455 different authors of scientific papers.

Number of attributes to display:
Create heatmap on all data Create heatmap on selection Save selection Load and create heatmap Perform