Abstract
The invention of fictional ideas (ideation) is often a central process in the creative production of artefacts such as poems, music and paintings, but has barely been studied in the computational creativity community. We present here a general approach to automated fictional ideation that works by manipulating facts specified in knowledge bases. More specifically, we specify a number of constructions which, by altering and combining facts from a knowledge base, result in the generation of fictions. Moreover, we present an instantiation of these constructions through the use of ConceptNet, a database of common sense knowledge. In order to evaluate the success of these constructions, we present a curation analysis that calculates the proportion of ideas which pass a typicality judgement. We further evaluate the output of this approach through a crowd-sourcing experiment in which participants were asked to rank ideas. We found a positive correlation between the participant’s rankings and a chaining inference technique that automatically assesses the value of the fictions generated through our approach. We believe that these results show that this approach constitutes a firm basis for automated fictional ideation with evaluative capacity.
Highlights
Ideation is a portmanteau word used to describe the process of generating a novel idea of value
During a pilot study reported in [19], we focused on ideas generated by the CO relation in the second ConceptNet node of flowchart B in Fig. 2; that is, we studied ideas of the type: ‘‘What if there was a little X, who couldn’t Y?’’ With an online survey of four questions, we asked 10 English-speaking participants to rank the same list of 15 such Disney characters, in terms of (a) general impression (GI) (b) emotional response (ER) provoked (c) narrative potential: number and quality of potential plot lines imaginable for the character, and (d) how surprising they found the character to be
While essential to the simulation of creative behaviour in software, fictional ideation has barely been studied in computational creativity research
Summary
Ideation is a portmanteau word used to describe the process of generating a novel idea of value. The work by Colton et al [4] reports on the automatic generation of poems, where the poem represents a response to articles from the Guardian newspaper. In both these cases, as in the majority of the systems developed so far within computational creativity research, there is no idea generation undertaken explicitly. The ISAAC system, developed by Moorman and Ram [26], implements a theory for creative understanding based on the use of an ontology to represent the dimensions of concepts. By altering the dimensions of existing concepts within the ontology, for instance considering a temporal object, e.g. the concept of days, as a physical one, the system is able to create novel concepts such as days that fly
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
