Database Reference
In-Depth Information
behind leaves. We have relied on it and trained it to survive for millennia and it
still surpasses automatic data mining methods to spot interesting patterns. Data
mining still needs to improve to match these pattern matching capabilities.
4.3 Automating or Not?
Is there a competition between confirmatory, automated and exploratory meth-
ods? No, they answer different questions. When a model is known in advance or
expected, using statistics is the right method. When a dataset becomes too large
to be visualized directly, automating some analysis is required. When exploring
a dataset in search of insights, information visualization should be used, possibly
in conjunction with data mining techniques if the dataset is too large.
Furthermore, combining data mining with visualization is the central issue of
Visual Analytics
, described by the paper
Visual Analytics: Definition, Process,
and Challenges
in this topic [6].
5 An Economical Model of Value
One important question is how to assess the value of visualization, ranging from
the evaluation of one specific use-case to the discipline in general. If we know
how to do this, then this might lead to an assessment of the current status as
well as the identification of success factors. An attempt was given by Van Wijk
[27] and is summarized here. After a short overview of his model, we discuss how
this model can be applied for InfoVis.
Visualization can be considered as a technology, a collection of methods,
techniques, and tools developed and applied to satisfy a need. Hence, standard
technological measures apply: Visualization has to be effective and ecient. To
measure these, an economic point of view is adopted. Instead of trying to un-
derstand why visualization works (see previous sections), here visualization is
considered from the outside, and an attempt is made to measure its profit. The
profit of visualization is defined as the difference between the value of the increase
in knowledge and the costs made to obtain this insight. Obviously, in practice
these are hard to quantify, but it is illuminating to attempt so. A schematic
model is considered: One visualization method
V
is used by
n
users to visual-
ize a data set
explorative steps. The
value of an increase in knowledge (or insight) has to be judged by the user.
Users can be satisfied intrinsically by new knowledge, as an enrichment of their
understanding of the world. A more pragmatic and operational point of view
is to consider if the new knowledge influences decisions, leads to actions, and,
hopefully, improves the quality of these. The overall gain now is
m
times each, where each session takes
k
nm
(
W
(
∆K
)),
where
)) represents the value of the increase in knowledge.
Concerning the costs for the use of (a specific) visualization
W
(
∆K
V
,thesecan
be split into various factors. Initial research and development costs
C
i
have to
be made; a user has to make initial costs
C
u
, because he has to spend time to
select and acquire
V
, and understand how to use it; per session initial costs
C
s
Search WWH ::
Custom Search