Baseline Methods for Automated Fictional Ideation

Llano, Maria Teresa; Hepworth, Rose; Colton, Simon; Gow, Jeremy; Lavrac, Nada; Znidarsic, Martin; Perovsek, Matic; Granoth-Wilding, Mark and Clark, Stephen. 2014. 'Baseline Methods for Automated Fictional Ideation'. In: 5th International Conference on Computational Creativity. Ljubljana, Slovenia 10-13 June 2014. [Conference or Workshop Item]

[img]
Preview
Text
COM-Llano2014b.pdf

Download (469kB) | Preview

Abstract or Description

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 three baseline approaches for automated fictional ideation, using methods which invert and alter facts from the ConceptNet and ReVerb databases, and perform bisociative discovery. For each method, we present a curation analysis, by calculating the proportion of ideas which pass a typicality evaluation. We further evaluate one ideation approach through a crowd- sourcing experiment in which participants were asked to rank ideas. The results from this study, and the baseline methods and methodologies presented here, constitute a firm basis on which to build more sophisticated models for automated ideation with evaluative capacity.

Item Type:

Conference or Workshop Item (Paper)

Departments, Centres and Research Units:

Computing

Dates:

DateEvent
2014Published

Event Location:

Ljubljana, Slovenia

Date range:

10-13 June 2014

Item ID:

17356

Date Deposited:

22 Mar 2016 09:14

Last Modified:

29 Apr 2020 16:15

URI:

https://research.gold.ac.uk/id/eprint/17356

View statistics for this item...

Edit Record Edit Record (login required)