Supporting Investigative Analysis through Visual Analytics

March 18, 2013
2:50 pm - 4:00 pm
196 Boston Ave (Room 4014)


Abstract: Today's analysts and researchers are faced with the daunting task of analyzing and understanding large amounts of data, often including textual documents and unstructured data. Sensemaking tasks, such as finding relevant pieces of information, formulating hypotheses, and combining facts to establish supporting or contradicting evidence, become more and more challenging as the data grow in size and complexity. Visual analytics aims at developing methods and tools that integrate computational approaches with interactive visualizations to support analysts in performing these types of sensemaking tasks. In this talk, I first briefly introduce the fields of investigative analysis and visual analytics and then discuss methods for the design, development, and evaluation of visual analytics systems in the context of the Jigsaw project. Jigsaw is a visual analytics system for exploring and understanding document collections. It represents documents and their entities visually in order to help analysts examine them more efficiently and develop theories more quickly. Jigsaw integrates computational text analyses, including document summarization, similarity, clustering, and sentiment analysis, with multiple coordinated views of documents and their entities. It has a special emphasis on visually illustrating connections between entities across the different documents.

Brief biography: Carsten Görg is a faculty member in the Computational Bioscience Program and in the Pharmacology Department in the University of Colorado Medical School. He received a Ph.D. in computer science from Saarland University, Germany in 2005 and worked as a Postdoctoral Fellow in the Graphics, Visualization & Usability Center at the Georgia Institute of Technology before joining the University of Colorado. Dr. Görg’s research interests include visual analytics and information visualization with a focus on designing, developing, and evaluating visual analytics tools to support the analysis of biological and biomedical datasets.