Title :
Explainers: Expert Explorations with Crafted Projections
Author :
Gleicher, Michael
Author_Institution :
Dept. of Comput. Sci., Univ. of Wisconsin - Madison, Madison, WI, USA
Abstract :
This paper introduces an approach to exploration and discovery in high-dimensional data that incorporates a user´s knowledge and questions to craft sets of projection functions meaningful to them. Unlike most prior work that defines projections based on their statistical properties, our approach creates projection functions that align with user-specified annotations. Therefore, the resulting derived dimensions represent concepts defined by the user´s examples. These especially crafted projection functions, or explainers, can help find and explain relationships between the data variables and user-designated concepts. They can organize the data according to these concepts. Sets of explainers can provide multiple perspectives on the data. Our approach considers tradeoffs in choosing these projection functions, including their simplicity, expressive power, alignment with prior knowledge, and diversity. We provide techniques for creating collections of explainers. The methods, based on machine learning optimization frameworks, allow exploring the tradeoffs. We demonstrate our approach on model problems and applications in text analysis.
Keywords :
data visualisation; learning (artificial intelligence); optimisation; crafted projection function; expert exploration; explainers; high-dimensional data; machine learning optimization framework; user-specified annotation; Cities and towns; Optimization; Quantization (signal); Support vector machines; Text mining; Cities and towns; High-dimensional spaces; Optimization; Quantization (signal); Support vector machines; Text mining; exploration; support vector machines; Algorithms; Artificial Intelligence; Computer Graphics; Expert Testimony; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; User-Computer Interface;
Journal_Title :
Visualization and Computer Graphics, IEEE Transactions on
DOI :
10.1109/TVCG.2013.157