Regent-Dependent Creativity: A Domain Independent Metric for the Assessment of Creative Artifacts

Humans are the ultimate judges on how creative is an artifact. In order to be creative, most researchers agree that an artifact has to be at least new and valuable. However, metrics to evaluate novelty and value are often craft for individual studies. Even within the same domain, these metrics commonly differ. Although this variety of metrics extends the spectrum of alternatives to assess creative artifacts, the lack of domain independent metrics makes hard to compare artifacts produced by different studies, which in turn slows down the research progress in the field. In this paper, we propose an domain independent metric, called Regent-Dependent Creativity (RDC), that assesses the creativity of artifacts. This metric requires that artifacts are described within the Regent-Dependent Model, in which artifacts features are represented as dependency pairs. RDC combines the Bayesian Surprise and Synergy to measure novelty and value, respectively. We show two case studies from different domains (fashion and games) to demonstrate how to model artifacts and assess creativity through RDC. We also propose and make available a simple API to promptly use RDC.

[1]  Florian Pinel,et al.  A Culinary Computational Creativity System , 2015 .

[2]  Kazjon Grace,et al.  What to expect when you're expecting: The role of unexpectedness in computationally evaluating creativity , 2014, ICCC.

[3]  Kai-Uwe Kühnberger,et al.  COINVENT: Towards a Computational Concept Invention Theory , 2014, ICCC.

[4]  Ashok K. Goel,et al.  Using Human Computation to Acquire Novel Methods for Addressing Visual Analogy Problems on Intelligence Tests , 2015, ICCC.

[5]  Douglas H. Fisher,et al.  USING AI TO EVALUATE CREATIVE DESIGNS , 2012 .

[6]  Ying Li,et al.  Exploring Application Domains for Computational Creativity , 2014, ICCC.

[7]  Anna Jordanous,et al.  Measuring cultural value using social network analysis: A case study on valuing electronic musicians , 2015, ICCC.

[8]  M. Boden.  The creative mind : myths & mechanisms , 1991 .

[9]  Charles L. A. Clarke,et al.  Human Competence in Creativity Evaluation , 2015, ICCC.

[10]  Mary Lou Maher,et al.  Evaluating creativity in humans, computers, and collectively intelligent systems , 2010, DESIRE.

[11]  Margaret A. Boden,et al.  Computer Models of Creativity , 2009, AI Mag..

[12]  Hugo Morais,et al.  HoningStone: Building Creative Combos With Honing Theory for a Digital Card Game , 2017, IEEE Transactions on Computational Intelligence and AI in Games.

[13]  Ian Millington,et al.  Artificial Intelligence for Games , 2006, The Morgan Kaufmann series in interactive 3D technology.

[14]  Michael A. Simon,et al.  Nature’s Magic: Synergy in Evolution and the Fate of Humankind.ByPeter Corning.Cambridge and New York: Cambridge University Press. $28.00. ix + 454 p; index. ISBN: 0–521–82547–4. 2003. , 2004 .

[15]  Terri Gullickson.  The Creative Mind: Myths and Mechanisms. , 1995 .

[16]  L. Gabora.  Revenge of the “Neurds”: Characterizing Creative Thought in Terms of the Structure and Dynamics of Memory , 2010, 1308.5037.

[17]  Oliver Bown,et al.  Attributing Creative Agency: Are we doing it right? , 2015, ICCC.

[18]  Simon Colton,et al.  Generating Code For Expressing Simple Preferences: Moving On From Hardcoding And Randomness , 2015, ICCC.

[19]  David Cope.  Computational Creativity and Music , 2015 .

[20]  Martin Schmettow,et al.  A Semantic Map for Evaluating Creativity , 2015, ICCC.

[21]  Kush R. Varshney,et al.  Cognition as a part of computational creativity , 2013, 2013 IEEE 12th International Conference on Cognitive Informatics and Cognitive Computing.

[22]  John K. Kruschke,et al.  Doing Bayesian Data Analysis: A Tutorial with R, JAGS, and Stan , 2014 .

[23]  J. Kruschke.  Doing Bayesian Data Analysis: A Tutorial with R and BUGS , 2010 .

[24]  Pierre Baldi,et al.  Bayesian surprise attracts human attention , 2005, Vision Research.

[25]  Kevin Burns,et al.  Computing the creativeness of amusing advertisements: A Bayesian model of Burma-Shave's muse , 2014, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[26]  Mateu Sbert,et al.  Conceptualizing Birkhoff's Aesthetic Measure Using Shannon Entropy and Kolmogorov Complexity , 2007, CAe.

[27]  Margaret A. Boden,et al.  Creativity and ALife , 2015, Artificial Life.

[28]  Simon Colton,et al.  Stakeholder Groups in Computational Creativity Research and Practice , 2015 .

[29]  Pierre Baldi,et al.  Of bits and wows: A Bayesian theory of surprise with applications to attention , 2010, Neural Networks.

[30]  Simon Colton,et al.  Assessing Progress in Building Autonomously Creative Systems , 2014, ICCC.

[31]  D. Krackhardt.  Graph theoretical dimensions of informal organizations , 1994 .

[32]  Martin Znidarsic,et al.  Implementation of a Slogan Generator , 2014, ICCC.

[33]  T. M. Amabile.  Social psychology of creativity: A consensual assessment technique. , 1982 .

[34]  Pythagoras Karampiperis,et al.  Towards Machines for Measuring Creativity: The Use of Computational Tools in Storytelling Activities , 2014, 2014 IEEE 14th International Conference on Advanced Learning Technologies.

[35]  Kevin Burns,et al.  Atoms of EVE′: A Bayesian basis for esthetic analysis of style in sketching , 2006, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.