Visual interactions with a multidimensional ranked list

Abstract

Performance analysis of an interactive visualization system generally requires an extensive user study, a method that is very expensive and that often yields inconclusive results. To do a successful user study, the researcher has to be well aware of the system's possibilities. We present a different kind of analysis. We show how the system behavior and performance could be investigated off-line, without user intervention. Combined with a user study such analysis may help the researcher to form an objective opinion of the system's abilities -to isolate what part of the system's performance is attributed to the system as compared to the user's skill. Motivation

An open source agenda for research linking text and image content features

“…Images that have been decomposed into their respective contents may then be clustered by any of several scaling methods (Han & Myaeng, 1996; Leouski & Allan, 1998). In the following example, we use a testbed of images from the Lyndon Baines Johnson Space Center of the National Aeronautics and Space Administration Space Transportation System Archives.…”

Shape recovery: A visual method for evaluation of information retrieval experiments

“…However, the technique was first proposed by Torgerson (1958). Evidence of the increasing use of MDS and visualization generally in IR analysis techniques appears in work by Leouski and Allan (1998), Mothe andDkaki (1998), andGrieff (1998). There have also been several recent dissertations exploring various dimensions of visualized retrieval.…”

Shape recovery: A visual method for evaluation of information retrieval experiments

“…However, the technique was first proposed by Torgerson (1958). Evidence of the increasing use of MDS and visualization generally in IR analysis techniques appears in work by Leouski and Allan (1998), Mothe and Dkaki (1998), and Grieff (1998). There have also been several recent dissertations exploring various dimensions of visualized retrieval.…”