Scaling Creative Inspiration with Fine-Grained Functional Aspects of Ideas
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Scaling Creative Inspiration with Fine-Grained Functional Aspects of Ideas. / Hope, Tom; Tamari, Ronen; Hershcovich, Daniel; Kang, Hyeonsu B.; Chan, Joel; Kittur, Aniket; Shahaf, Dafna.
CHI 2022 - Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, Inc., 2022. p. 1-15 12.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Scaling Creative Inspiration with Fine-Grained Functional Aspects of Ideas
AU - Hope, Tom
AU - Tamari, Ronen
AU - Hershcovich, Daniel
AU - Kang, Hyeonsu B.
AU - Chan, Joel
AU - Kittur, Aniket
AU - Shahaf, Dafna
N1 - Publisher Copyright: © 2022 ACM.
PY - 2022
Y1 - 2022
N2 - Large repositories of products, patents and scientific papers offer an opportunity for building systems that scour millions of ideas and help users discover inspirations. However, idea descriptions are typically in the form of unstructured text, lacking key structure that is required for supporting creative innovation interactions. Prior work has explored idea representations that were either limited in expressivity, required significant manual effort from users, or dependent on curated knowledge bases with poor coverage. We explore a novel representation that automatically breaks up products into fine-grained functional aspects capturing the purposes and mechanisms of ideas, and use it to support important creative innovation interactions: functional search for ideas, and exploration of the design space around a focal problem by viewing related problem perspectives pooled from across many products. In user studies, our approach boosts the quality of creative search and inspirations, substantially outperforming strong baselines by 50-60%.
AB - Large repositories of products, patents and scientific papers offer an opportunity for building systems that scour millions of ideas and help users discover inspirations. However, idea descriptions are typically in the form of unstructured text, lacking key structure that is required for supporting creative innovation interactions. Prior work has explored idea representations that were either limited in expressivity, required significant manual effort from users, or dependent on curated knowledge bases with poor coverage. We explore a novel representation that automatically breaks up products into fine-grained functional aspects capturing the purposes and mechanisms of ideas, and use it to support important creative innovation interactions: functional search for ideas, and exploration of the design space around a focal problem by viewing related problem perspectives pooled from across many products. In user studies, our approach boosts the quality of creative search and inspirations, substantially outperforming strong baselines by 50-60%.
UR - http://www.scopus.com/inward/record.url?scp=85130576013&partnerID=8YFLogxK
U2 - 10.1145/3491102.3517434
DO - 10.1145/3491102.3517434
M3 - Article in proceedings
AN - SCOPUS:85130576013
SP - 1
EP - 15
BT - CHI 2022 - Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems
PB - Association for Computing Machinery, Inc.
T2 - 2022 CHI Conference on Human Factors in Computing Systems, CHI 2022
Y2 - 30 April 2022 through 5 May 2022
ER -
ID: 339853860