Mining for creativity: Determining the creativity of ideas through data mining techniques

Christine A. Toh, Elizabeth M. Starkey, Conrad S. Tucker, Scarlett Rae Miller

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

The emergence of ideation methods that generate large volumes of early-phase ideas has led to a need for reliable and efficient metrics for measuring the creativity of these ideas. However, existing methods of human judgment-based creativity assessments, as well as numeric model-based creativity assessment approaches suffer from low reliability and prohibitive computational burdens on human raters due to the high level of human input needed to calculate creativity scores. In addition, there is a need for an efficient method of computing the creativity of large sets of design ideas typically generated during the design process. This paper focuses on developing and empirically testing a machine learning approach for computing design creativity of large sets of design ideas to increase the efficiency and reliability of creativity evaluation methods in design research. The results of this study show that machine learning techniques can predict creativity of ideas with relatively high accuracy and sensitivity. These findings show that machine learning has the potential to be used for rating the creativity of ideas generated based on their descriptions.

Original languageEnglish (US)
Title of host publication29th International Conference on Design Theory and Methodology
PublisherAmerican Society of Mechanical Engineers (ASME)
Volume7
ISBN (Electronic)9780791858219
DOIs
StatePublished - Jan 1 2017
EventASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2017 - Cleveland, United States
Duration: Aug 6 2017Aug 9 2017

Other

OtherASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2017
CountryUnited States
CityCleveland
Period8/6/178/9/17

Fingerprint

Data mining
Mining
Data Mining
Learning systems
Machine Learning
Large Set
Creativity
Computing
Evaluation Method
Numerics
Testing
Design Process
High Accuracy
Model-based
Calculate
Metric
Predict
Design
Human

All Science Journal Classification (ASJC) codes

  • Mechanical Engineering
  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Modeling and Simulation

Cite this

Toh, C. A., Starkey, E. M., Tucker, C. S., & Miller, S. R. (2017). Mining for creativity: Determining the creativity of ideas through data mining techniques. In 29th International Conference on Design Theory and Methodology (Vol. 7). American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/DETC2017-68304
Toh, Christine A. ; Starkey, Elizabeth M. ; Tucker, Conrad S. ; Miller, Scarlett Rae. / Mining for creativity : Determining the creativity of ideas through data mining techniques. 29th International Conference on Design Theory and Methodology. Vol. 7 American Society of Mechanical Engineers (ASME), 2017.
@inproceedings{c23cb0ee654b405f9f9ccb2ac8a5e774,
title = "Mining for creativity: Determining the creativity of ideas through data mining techniques",
abstract = "The emergence of ideation methods that generate large volumes of early-phase ideas has led to a need for reliable and efficient metrics for measuring the creativity of these ideas. However, existing methods of human judgment-based creativity assessments, as well as numeric model-based creativity assessment approaches suffer from low reliability and prohibitive computational burdens on human raters due to the high level of human input needed to calculate creativity scores. In addition, there is a need for an efficient method of computing the creativity of large sets of design ideas typically generated during the design process. This paper focuses on developing and empirically testing a machine learning approach for computing design creativity of large sets of design ideas to increase the efficiency and reliability of creativity evaluation methods in design research. The results of this study show that machine learning techniques can predict creativity of ideas with relatively high accuracy and sensitivity. These findings show that machine learning has the potential to be used for rating the creativity of ideas generated based on their descriptions.",
author = "Toh, {Christine A.} and Starkey, {Elizabeth M.} and Tucker, {Conrad S.} and Miller, {Scarlett Rae}",
year = "2017",
month = "1",
day = "1",
doi = "10.1115/DETC2017-68304",
language = "English (US)",
volume = "7",
booktitle = "29th International Conference on Design Theory and Methodology",
publisher = "American Society of Mechanical Engineers (ASME)",

}

Toh, CA, Starkey, EM, Tucker, CS & Miller, SR 2017, Mining for creativity: Determining the creativity of ideas through data mining techniques. in 29th International Conference on Design Theory and Methodology. vol. 7, American Society of Mechanical Engineers (ASME), ASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2017, Cleveland, United States, 8/6/17. https://doi.org/10.1115/DETC2017-68304

Mining for creativity : Determining the creativity of ideas through data mining techniques. / Toh, Christine A.; Starkey, Elizabeth M.; Tucker, Conrad S.; Miller, Scarlett Rae.

29th International Conference on Design Theory and Methodology. Vol. 7 American Society of Mechanical Engineers (ASME), 2017.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Mining for creativity

T2 - Determining the creativity of ideas through data mining techniques

AU - Toh, Christine A.

AU - Starkey, Elizabeth M.

AU - Tucker, Conrad S.

AU - Miller, Scarlett Rae

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The emergence of ideation methods that generate large volumes of early-phase ideas has led to a need for reliable and efficient metrics for measuring the creativity of these ideas. However, existing methods of human judgment-based creativity assessments, as well as numeric model-based creativity assessment approaches suffer from low reliability and prohibitive computational burdens on human raters due to the high level of human input needed to calculate creativity scores. In addition, there is a need for an efficient method of computing the creativity of large sets of design ideas typically generated during the design process. This paper focuses on developing and empirically testing a machine learning approach for computing design creativity of large sets of design ideas to increase the efficiency and reliability of creativity evaluation methods in design research. The results of this study show that machine learning techniques can predict creativity of ideas with relatively high accuracy and sensitivity. These findings show that machine learning has the potential to be used for rating the creativity of ideas generated based on their descriptions.

AB - The emergence of ideation methods that generate large volumes of early-phase ideas has led to a need for reliable and efficient metrics for measuring the creativity of these ideas. However, existing methods of human judgment-based creativity assessments, as well as numeric model-based creativity assessment approaches suffer from low reliability and prohibitive computational burdens on human raters due to the high level of human input needed to calculate creativity scores. In addition, there is a need for an efficient method of computing the creativity of large sets of design ideas typically generated during the design process. This paper focuses on developing and empirically testing a machine learning approach for computing design creativity of large sets of design ideas to increase the efficiency and reliability of creativity evaluation methods in design research. The results of this study show that machine learning techniques can predict creativity of ideas with relatively high accuracy and sensitivity. These findings show that machine learning has the potential to be used for rating the creativity of ideas generated based on their descriptions.

UR - http://www.scopus.com/inward/record.url?scp=85035318984&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85035318984&partnerID=8YFLogxK

U2 - 10.1115/DETC2017-68304

DO - 10.1115/DETC2017-68304

M3 - Conference contribution

AN - SCOPUS:85035318984

VL - 7

BT - 29th International Conference on Design Theory and Methodology

PB - American Society of Mechanical Engineers (ASME)

ER -

Toh CA, Starkey EM, Tucker CS, Miller SR. Mining for creativity: Determining the creativity of ideas through data mining techniques. In 29th International Conference on Design Theory and Methodology. Vol. 7. American Society of Mechanical Engineers (ASME). 2017 https://doi.org/10.1115/DETC2017-68304