Discovering technology and science innovation opportunity based on sentence generation algorithm

Taeyeoun Roh and Byungun Yoon

Journal of Informetrics, 2023, vol. 17, issue 2

Abstract: Science and technology are crucial elements in discovering innovation opportunities. They have their own practical and theoretical unique meaning in innovation factors. Scientific or technological information can be collected by patents or papers, and various approaches for innovation opportunities discovery are being proposed using text mining. Since a previous methodology using patents and papers discovered opportunities in science or technology itself, they cannot discover opportunities reflecting the science and technology relationship. In addition, since discovered innovation opportunities are formed within the keyword or phrase level, they cannot provide innovation direction or purpose. Therefore, this study suggests a new approach to discovering science and technology innovation opportunities that reflects the science–technology relationship and their concrete directions/purposes using the sentence generation algorithm. An algorithm-generated sentence can contain contextual flow and connection between keywords. In contrast, the generated sentences from the sentence model can reflect science and technology from mass data in a readable sentence. Key innovation factors from science and technology are extracted from generated sentences and then innovation opportunities with specific directions and purposes are suggested.

Keywords: Technology innovation; Science innovation; Innovation opportunity; Sentence Generation (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1751157723000287
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:infome:v:17:y:2023:i:2:s1751157723000287

DOI: 10.1016/j.joi.2023.101403

Access Statistics for this article

Journal of Informetrics is currently edited by Leo Egghe

More articles in Journal of Informetrics from Elsevier
Bibliographic data for series maintained by Catherine Liu ().