Document Type
Conference Proceeding
Publication Date
1-1-2019
Journal / Book Title
Proceedings of the Annual Hawaii International Conference on System Sciences
Abstract
In crowdsourcing ideation websites, companies can easily collect large amount of ideas. Screening through such volume of ideas is very costly and challenging, necessitating automatic approaches. It would be particularly useful to automatically evaluate idea novelty since companies commonly seek novel ideas. Three computational approaches were tested, based on Latent Semantic Analysis (LSA), Latent Dirichlet Allocation (LDA) and term frequency-inverse document frequency (TF-IDF), respectively. These three approaches were used on three set of ideas and the computed idea novelty was compared with human expert evaluation. TF-IDF based measure correlated better with expert evaluation than the other two measures. However, our results show that these approaches do not match human judgement well enough to replace it.
DOI
10.24251/HICSS.2019.111
Montclair State University Digital Commons Citation
Wang, Kai; Dong, Boxiang; and Ma, Junjie, "Towards computational assessment of idea novelty" (2019). Department of Computer Science Faculty Scholarship and Creative Works. 778.
https://digitalcommons.montclair.edu/compusci-facpubs/778
Rights
This article is Open Access and distributed under a Creative Commons 4.0 license.
Published Citation
Wang, K., Dong, B., & Ma, J. (2019, May). Towards computational assessment of idea novelty. In Proceedings of the 52nd Hawaii international conference on system sciences.