Database Reference
In-Depth Information
Visual Analytics versus Information Visualization
Many people are confused by the new term visual analytics and do not see a dif-
ference between the two areas. While there is certainly some overlay and some of
the information visualization work is certainly highly related to visual analytics,
traditional visualization work does not necessarily deal with an analysis tasks
nor does it always also use advanced data analysis algorithms.
Visual analytics is more than just visualization. It can rather be seen as an
integral approach to decision-making, combining visualization, human factors
and data analysis. The challenge is to identify the best automated algorithm for
the analysis task at hand, identify its limits which can not be further automated,
and then develop a tightly integrated solution with adequately integrates the best
automated analysis algorithms with appropriate visualization and interaction
techniques.
While some of such research has been done within the visualization commu-
nity in the past, the degree to which advanced knowledge discovery algorithms
have been employed is quite limited. The idea of visual analytics is to funda-
mentally change that. This will help to focus on the right part of the problem,
i.e. the parts that can not be solved automatically, and will provide solutions to
problems that we were not able to solve before.
One important remark should be made here. Most research efforts in Infor-
mation Visualization have concentrated on the process of producing views and
creating valuable interaction techniques for a given class of data (social network,
multi-dimensional data, etc.). However, much less has been suggested as to how
user interactions on the data can be turned into intelligence to tune underlying
analytical processes. A system might for instance observe that most of the user's
attention concern only a subpart of an ontology (through queries or by repeated
direct manipulations of the same graphical elements, for instance). Why not then
use this knowledge about the user's interest and update various parameters by
the system (trying to systematically place elements or components of interest in
center view, even taking this fact into account when driving a clustering algo-
rithm with a modularity quality criteria, for instance).
This is one place where Visual Analytics maybe differs most from Information
Visualization, giving higher priority to data analytics from the start and through
all iterations of the sense making loop. Creativity is then needed to understand
how perception issues can help bring more intelligence into the analytical process
by “learning” from users' behavior and effective use of the visualization.
3 Areas Related to Visual Analytics
Visual analytics builds on a variety of related scientific fields. At its heart, Visual
Analytics integrates Information and Scientific Visualization with Data Manage-
ment and Data Analysis Technology, as well as Human Perception and Cognition
research. For effective research, Visual Analytics also requires an appropriate In-
frastructure in terms of software and data sets and related analytical problems
repositories, and to develop reliable Evaluation methodology (see Figure 3).
Search WWH ::
Custom Search