Issue No. 05 - September/October (1999 vol. 19)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/38.788797
Visual data mining requires a tightly coupled visual interface with underlying information retrieval and analysis engines. To be useful, these techniques must augment human exploration and discovery beyond existing methods. Since the focus of data mining is to <p>provide humans with supporting tools to think and explore, human perceptual issues are an important component of effective visual interfaces for such systems.</p> <p>In this article we describe a shape-based visual interface for information retrieval and interactive exploration. Our exploratory system uses procedurally generated shapes coupled with an underlying text retrieval engine. Traditional text-based queries and summarization are enhanced with a visual interface based on 3D shapes (glyphs). Our interface allows visualizing multidimensional relationships among documents and perceiving more information than with conventional text-based interfaces. It promotes information overview and "drill-down" in support of analysis. Before describing our visual interface and application, we introduce information retrieval within the context of data mining and provide a brief over-view of procedural shape generation. We then describe our current system and give a few relevant examples. Finally, we offer some ideas for future enhancements and direction.</p>
J. L. Sibert, D. S. Ebert and R. M. Rohrer, "A Shape-Based Visual Interface for Text Retrieval," in IEEE Computer Graphics and Applications, vol. 19, no. , pp. 40-46, 1999.