Mixing Evaluation Methods for Assessing the Utility of an Interactive InfoVis Technique

Abstract. We describe the results of an empirical study comparing an interactive Information Visualization (InfoVis) technique called Gravi++ (GRAVI), Exploratory Data Analysis (EDA) and Machine Learning (ML). The application domain is the psychotherapeutic treatment of anorectic young women. The three techniques are supposed to support the therapists in finding the variables which influence success or failure in therapy. To evaluate the utility of the three techniques we developed on the one hand a report system which helped subjects to formulate and document in a self-directed manner the insights they gained when using the three techniques. On the other hand, focus groups were held with the subjects. The combination of these very different evaluation methods prevents jumping to false conclusions and enables for an comprehensive assessment of the tested techniques. The combined results indicate that the three techniques (EDA, ML, and GRAVI) are complementary and therefore should be ...

• Type: Conference
• Year: 2007
• Where: HCI
• Authors: Markus Rester, Margit Pohl, Sylvia Wiltner, Klaus Hinum, Silvia Miksch, Christian Popow, Susanne Ohmann
• Keywords: Exploratory Data Analysis, HCI 2007, Human Computer Interaction, Interactive Information Visualization, Technique Called Gravi++