[The original web site of the WHIM project is down. This stub has been created to provide basic information about it.]
The WHIM project was a A 3 year project funded by the European Comission STREP FP7 program to address objective ICT-2013.8.1: Technologies and scientific foundations in the field of creativity. It took place from October 2013 to September 2016.
The main output of the WHIM project, the WhatIf Machine for creative ideation and the PropperWryter software that was created as a result of the work in Work Package 4 oin Narrative Evaluation of Ideas were employed in the generation of "Beyond the Fence", the first musical generated by computer. "Beyond the Fence" had 15 performances at the Arts Theater in the London West End between 22nd February and March 3rd 2016.
Some basic information about the project has been compiled below.
Original Project Abstract
In Computational Creativity research, we study how to engineer software which can take on some of the creative
responsibility in arts and science projects. There has been much progress towards the creative generation of
artefacts of cultural value such as poems, music and paintings. Often, when produced by people, such artefacts
embed a fictional idea invented by the creator. For instance, an artist might have the fictional idea: [What if there
was a quiz show, where each week someone was shot dead?] and express this through a painting, poem or
film. While such ideation is clearly central to creativity, with obvious applications to the creative industries, there
have only been a few small, ad-hoc studies of how to automate fictional ideation. The time is therefore ripe
to see whether we can derive, implement and test novel formalisms and processes which enable software to
not only invent, but assess, explore and present such ideas. We propose to investigate the following model for
creative idea generation: (a) collect and analyse some information about a domain, to form a shallow world view
of that domain (b) form a set of what-if style ideas from the analysis using notions of surprise, semantic tension
and incongruity (c) assess, rank and select ideas based on the quality and quantity of narratives that can be
generated using each idea, and (d) use the world view, idea and narratives in linguistic renderings, taking into
account notions of relevancy, expansion, obfuscation and affect. Given that ideas are for human consumption,
we will also collect crowd-sourced data about how people value, appreciate and expand these ideas, and will
machine learn predictors for how people will react to automatically generated ideas. We expect this project to not
only bring into being a new era of idea-centric approaches to Computational Creativity, but also to highlight to
creative industry practitioners the huge potential of creative software collaborators.
List of partners
- Goldsmitsh College (London, United Kingdom) [Coordinator]
- Universidad Complutense de Madrid (Spain)
- University of Cambridge (United Kingdom)
- Institut Jozef Stefan (Lubljana, Slovenia)
- University College Dublin (Ireland)
Work packages
- WP 1 Project Management
- WP 2 World View Building
- WP 3 Automated Ideation and What-If Scenario Generation
- WP 4 Narrative-based Evaluation of Ideas
- WP 5 Rendering of Ideas
- WP 6 Data-Mining Audience Evaluation of Ideas
- WP 7 Dissemination and Exploitation of Results
Description of UCM Contribution
Within the WHIM project, UCM was leader of Work Package 4 on Narrative-based Evaluation of Ideas. This resulted in the development of a number of metrics for evaluating narrative quality and the PropperWryter system for the automated construction of plots. Details on these research efforts may be found under the publications section of this web site.