Text Mining to Measure Novelty and Diffusion of Technological Inventions

Arts, Sam; Hou, Jianan; Gomez, Juan Charlos

doi:10.34726/pst2019.2

Record link:

https://doi.org/10.34726/pst2019.2
http://hdl.handle.net/20.500.12708/833

Title:

Text Mining to Measure Novelty and Diffusion of Technological Inventions

Citation:

Arts, S., Hou, J., & Gomez, J. C. (2019). Text Mining to Measure Novelty and Diffusion of Technological Inventions. In Proceedings of The 1st Workshop on Patent Text Mining and Semantic Technologies (PatentSemTech 2019). 1st Workshop on Patent Text Mining and Semantic Technologies (PatentSemTech 2019), Karlsruhe, Germany. https://doi.org/10.34726/pst2019.2

reposiTUm DOI:

10.34726/pst2019.2

CatalogPlus:

AC15614218

Publication Type:

Inproceedings - Full-Paper Contribution

Language:

English

Authors:

Arts, Sam
Hou, Jianan
Gomez, Juan Charlos

Published in:

Proceedings of The 1st Workshop on Patent Text Mining and Semantic Technologies (PatentSemTech 2019)

Date (published):

2019

Event name:

1st Workshop on Patent Text Mining and Semantic Technologies (PatentSemTech 2019)

Event date:

12-Sep-2019

Event place:

Karlsruhe, Germany

Number of Pages:

Keywords:

patent; text; natural language processing; novelty; impact; indicator

Additional information:

Traditional measures of patent novelty and diffusion mostly rely on patent classification or citation information. Given that inventive ideas are embedded in the text of patent documents, our study validates different alternative natural language processing techniques to measure the novelty and diffusion of technological inventions. As a validation test, we collect a set of patents linked to famous awards such as the Nobel prize. Overall, text-based measures outperform other commonly-used novelty and diffusion metrics.

License:

CC BY 4.0