May AI?: Design Ideation with Cooperative Contextual Bandits

Design ideation is a prime creative activity in design. However, it is challenging to support computationally due to its quickly evolving and exploratory nature. The paper presents cooperative contextual bandits (CCB) as a machine-learning method for interactive ideation support. A CCB can learn to propose domain-relevant contributions and adapt their exploration/exploitation strategy. We developed a CCB for an interactive design ideation tool that 1) suggests inspirational and situationally relevant materials ("may AI?"); 2) explores and exploits inspirational materials with the designer; and 3) explains its suggestions to aid reflection. The application case of digital mood board design is presented, wherein visual inspirational materials are collected and curated in collages. In a controlled study, 14 of 16 professional designers preferred the CCB-augmented tool. The CCB approach holds promise for ideation activities wherein adaptive and steerable support is welcome but designers must retain full outcome control.

[1]  Elizabeth Gerber,et al.  Momentum: getting and staying on topic during a brainstorm , 2010, CHI.

[2]  Andrés Lucero,et al.  Framing, aligning, paradoxing, abstracting, and directing: how design mood boards work , 2012, DIS '12.

[3]  Pieter Jan Stappers,et al.  Collections designers keep: Collecting visual material for inspiration and reference , 2006 .

[4]  Jun Rekimoto,et al.  V8 Storming: How Far Should Two Ideas Be? , 2018, AH.

[5]  Jun Xiao,et al.  Mixed-initiative photo collage authoring , 2008, ACM Multimedia.

[6]  Andrés Lucero,et al.  Surfing for Inspiration: digital inspirational material in design practice , 2018, DRS2018: Catalyst.

[7]  Dorota Glowacka,et al.  Interactive Intent Modeling from Multiple Feedback Domains , 2016, IUI.

[8]  A. Lucero,et al.  Augmenting Mood Boards: Flexible and Intuitive Interaction in the Context of the Design Studio , 2007, Second Annual IEEE International Workshop on Horizontal Interactive Human-Computer Systems (TABLETOP'07).

[9]  Nigel Cross,et al.  Creativity in the design process: co-evolution of problem–solution , 2001 .

[10]  Andrés Lucero.  Funky-Design-Spaces: Interactive Environments for Creativity Inspired by Observing Designers Making Mood Boards , 2015, INTERACT.

[11]  Diogo Cabral,et al.  InspirationWall: Supporting Idea Generation Through Automatic Information Exploration , 2015, Creativity & Cognition.

[12]  Petra Badke-Schaub,et al.  Inspiration choices that matter: the selection of external stimuli during ideation , 2016, Design Science.

[13]  Krzysztof Z. Gajos,et al.  Providing Timely Examples Improves the Quantity and Quality of Generated Ideas , 2015, Creativity & Cognition.

[14]  Antonios Liapis,et al.  Mixed-initiative co-creativity , 2014, FDG.

[15]  Belinda Thom,et al.  BoB: an interactive improvisational music companion , 2000, AGENTS '00.

[16]  Brian Magerko,et al.  Viewpoints AI: Procedurally Representing and Reasoning about Gestures , 2013, DiGRA Conference.

[17]  Shuchang Zhou,et al.  EAST: An Efficient and Accurate Scene Text Detector , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Sébastien Bubeck,et al.  Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems , 2012, Found. Trends Mach. Learn..

[19]  Desney S. Tan,et al.  CueFlik: interactive concept learning in image search , 2008, CHI.

[20]  P. Mazzarello,et al.  What dreams may come? , 2000, Nature.

[21]  David R. Karger,et al.  Scatter/Gather: a cluster-based approach to browsing large document collections , 1992, SIGIR '92.

[22]  Philippa Mothersill,et al.  An Ontology of Computational Tools for Design Activities , 2018, DRS2018: Catalyst.

[23]  Tracy Diane Cassidy,et al.  The Mood Board Process Modeled and Understood as a Qualitative Design Research Tool , 2011 .

[24]  Deana McDonagh-Philp,et al.  Problem Interpretation and Resolution via Visual Stimuli: The Use of ‘Mood Boards’ in Design Education , 2001 .

[25]  Dafna Shahaf,et al.  Analogy Mining for Specific Design Needs , 2017, CHI.

[26]  Sungwoo Lee,et al.  I Lead, You Help but Only with Enough Details: Understanding User Experience of Co-Creation with Artificial Intelligence , 2018, CHI.

[27]  C. Peirce,et al.  Collected Papers of Charles Sanders Peirce , 1936, Nature.

[28]  James Fogarty,et al.  Aesthetic information collages: generating decorative displays that contain information , 2001, UIST '01.

[29]  Celine Latulipe,et al.  Quantifying the Creativity Support of Digital Tools through the Creativity Support Index , 2014, ACM Trans. Comput. Hum. Interact..

[30]  Wei Chu,et al.  A contextual-bandit approach to personalized news article recommendation , 2010, WWW '10.

[31]  Dzmitry Aliakseyeu,et al.  An interactive support tool to convey the intended message in asynchronous presentations , 2009, Advances in Computer Entertainment Technology.

[32]  Mihaela van der Schaar,et al.  Distributed Online Learning via Cooperative Contextual Bandits , 2013, IEEE Transactions on Signal Processing.

[33]  Jami J. Shah,et al.  Understanding design ideation mechanisms through multilevel aligned empirical studies , 2010 .

[34]  Ben Jonson,et al.  Design ideation: the conceptual sketch in the digital age , 2005 .

[35]  Andrew M. Webb,et al.  Patterns of Free-form Curation: Visual Thinking with Web Content , 2016, ACM Multimedia.

[36]  Brian Magerko,et al.  Empirically Studying Participatory Sense-Making in Abstract Drawing with a Co-Creative Cognitive Agent , 2016, IUI.

[37]  Simone Bianco,et al.  User Preferences Modeling and Learning for Pleasing Photo Collage Generation , 2015, TOMM.

[38]  Ben Shneiderman,et al.  Creativity support tools: accelerating discovery and innovation , 2007, CACM.

[39]  Krzysztof Z. Gajos,et al.  Semantically Far Inspirations Considered Harmful?: Accounting for Cognitive States in Collaborative Ideation , 2017, Creativity & Cognition.

[40]  Martin Schrepp,et al.  Construction and Evaluation of a User Experience Questionnaire , 2008, USAB.

[41]  Antonella De Angeli,et al.  Quantification of interface visual complexity , 2014, AVI.