On the Role of Computers in Creativity-Support Systems - Computational Creativity Research: Towards Creative Machines - page 111

Task

home

PPB Home studio

does not
exist

is
required

Ratio
decidendi

is
important

space provided by
the employer

takes most
time

for a professor
research is important

Intermediate
level

place3

place1

taxpayer
educator

task1

employer place2

task2

place4

City
College

library

Weissman classroom

research

teaching

professor

home

Facts

Fig. 6.4 Drucker case applied to the Weissman case ( Dashed lines means provided by, dotted
lines mean designated space for, and dot-dash lines means performed at. PPB is principal place of
business .)

representations used in these examples were derived from actual opinions written by
the judges when rendering their decisions.
The implications of this for computational systems is that we need to be able to
model the process of reinterpretation, by which concepts and categories are applied
to different data (for which they may not have been intended) in novel ways. This is
consistent with recent research that suggests psychological distance as a mechanism
for enhancing creativity [ 60 ]. Moreover, it has been demonstrated that psychological
distance can be induced by such simple devices as taking another person's perspective
or thinking of the problem as if it is unreal [ 35 ].
It is interesting to point out that the ability to get a new insight or perspective was
one of the advantages claimed for case-based reasoning when it was promoted by
Riesbeck and Schank ([ 53 , pp. 9-14]). They compared and contrasted three modes of
reasoning: (1) reasoning with ossified cases (rules or abstract principles), (2) reason-
ing with paradigmatic cases (cases with a given interpretation), and (3) reasoning with
stories (cases with many possible interpretations and capable of re-interpretations).
They argued that it is the third mode of reasoning that displays the most flexibility
and power of having a knowledge base containing cases. However, most approaches
to case-based reasoning in the 1990s and early part of the 2000s worked largely with
indexed cases, which precludes this reinterpretation step. (See, for instance [ 6 ].) But
in recent years, advances in data mining and unsupervised learning techniques pro-