Topic modelling approach to knowledge depth and breadth: Analyzing trajectories of technological knowledge

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

Technology assessment and planning requires that we can reliably, but indirectly, measure knowledge embedded in the organization. Operationalizing knowledge embedded into companies is increasingly challenging but also more and more relevant in the current cross-disciplinary and complex technological environment. Existing approaches for operationalizing company knowledge are based on patent data and analyzing patent classifications. These approaches have, however, significant limitations. In this study, knowledge depth and breadth is studied using full-text patent data from seven large telecommunication companies totaling 157,718 patents. The data was analyzed with Latent Dirichlet Allocation, an unsupervised learning method. The results are quantified using a technological diversity metric, showing temporal changes in companies knowledge. The result show how the operationalization of company knowledge is independent of patent count and that companies have their specific trajectory of knowledge development. The approach offers a novel method of analyzing the knowledge trajectory of a company, compared to existing patent classification based methods.
Original languageEnglish
Title of host publication2017 IEEE Technology and Engineering Management Society Conference, TEMSCON 2017
PublisherInstitute of Electrical and Electronic Engineers IEEE
Pages55-60
Number of pages6
ISBN (Electronic)978-1-5090-1114-8
ISBN (Print)978-1-5090-1115-5
DOIs
Publication statusPublished - 31 Jul 2017
MoE publication typeA4 Article in a conference publication
EventIEEE Technology & Engineering Management Conference, TEMSCON 2017 - Santa Clara, United States
Duration: 8 Jun 201710 Jun 2017

Conference

ConferenceIEEE Technology & Engineering Management Conference, TEMSCON 2017
Abbreviated titleTEMSCON 2017
CountryUnited States
CitySanta Clara
Period8/06/1710/06/17

Fingerprint

Trajectories
Industry
Unsupervised learning
Technological knowledge
Trajectory
Modeling
Patents
Telecommunication
Planning
Patent data

Keywords

  • patents
  • companies
  • portfolios
  • communications technology
  • unsupervised learning
  • trajectory
  • time series analysis

Cite this

Suominen, A. (2017). Topic modelling approach to knowledge depth and breadth: Analyzing trajectories of technological knowledge. In 2017 IEEE Technology and Engineering Management Society Conference, TEMSCON 2017 (pp. 55-60). [7998354] Institute of Electrical and Electronic Engineers IEEE. https://doi.org/10.1109/TEMSCON.2017.7998354
Suominen, Arho. / Topic modelling approach to knowledge depth and breadth: Analyzing trajectories of technological knowledge. 2017 IEEE Technology and Engineering Management Society Conference, TEMSCON 2017. Institute of Electrical and Electronic Engineers IEEE, 2017. pp. 55-60
@inproceedings{96da60c4fee64270a657831417d1ad0d,
title = "Topic modelling approach to knowledge depth and breadth: Analyzing trajectories of technological knowledge",
abstract = "Technology assessment and planning requires that we can reliably, but indirectly, measure knowledge embedded in the organization. Operationalizing knowledge embedded into companies is increasingly challenging but also more and more relevant in the current cross-disciplinary and complex technological environment. Existing approaches for operationalizing company knowledge are based on patent data and analyzing patent classifications. These approaches have, however, significant limitations. In this study, knowledge depth and breadth is studied using full-text patent data from seven large telecommunication companies totaling 157,718 patents. The data was analyzed with Latent Dirichlet Allocation, an unsupervised learning method. The results are quantified using a technological diversity metric, showing temporal changes in companies knowledge. The result show how the operationalization of company knowledge is independent of patent count and that companies have their specific trajectory of knowledge development. The approach offers a novel method of analyzing the knowledge trajectory of a company, compared to existing patent classification based methods.",
keywords = "patents, companies, portfolios, communications technology, unsupervised learning, trajectory, time series analysis",
author = "Arho Suominen",
year = "2017",
month = "7",
day = "31",
doi = "10.1109/TEMSCON.2017.7998354",
language = "English",
isbn = "978-1-5090-1115-5",
pages = "55--60",
booktitle = "2017 IEEE Technology and Engineering Management Society Conference, TEMSCON 2017",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
address = "United States",

}

Suominen, A 2017, Topic modelling approach to knowledge depth and breadth: Analyzing trajectories of technological knowledge. in 2017 IEEE Technology and Engineering Management Society Conference, TEMSCON 2017., 7998354, Institute of Electrical and Electronic Engineers IEEE, pp. 55-60, IEEE Technology & Engineering Management Conference, TEMSCON 2017, Santa Clara, United States, 8/06/17. https://doi.org/10.1109/TEMSCON.2017.7998354

Topic modelling approach to knowledge depth and breadth: Analyzing trajectories of technological knowledge. / Suominen, Arho.

2017 IEEE Technology and Engineering Management Society Conference, TEMSCON 2017. Institute of Electrical and Electronic Engineers IEEE, 2017. p. 55-60 7998354.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Topic modelling approach to knowledge depth and breadth: Analyzing trajectories of technological knowledge

AU - Suominen, Arho

PY - 2017/7/31

Y1 - 2017/7/31

N2 - Technology assessment and planning requires that we can reliably, but indirectly, measure knowledge embedded in the organization. Operationalizing knowledge embedded into companies is increasingly challenging but also more and more relevant in the current cross-disciplinary and complex technological environment. Existing approaches for operationalizing company knowledge are based on patent data and analyzing patent classifications. These approaches have, however, significant limitations. In this study, knowledge depth and breadth is studied using full-text patent data from seven large telecommunication companies totaling 157,718 patents. The data was analyzed with Latent Dirichlet Allocation, an unsupervised learning method. The results are quantified using a technological diversity metric, showing temporal changes in companies knowledge. The result show how the operationalization of company knowledge is independent of patent count and that companies have their specific trajectory of knowledge development. The approach offers a novel method of analyzing the knowledge trajectory of a company, compared to existing patent classification based methods.

AB - Technology assessment and planning requires that we can reliably, but indirectly, measure knowledge embedded in the organization. Operationalizing knowledge embedded into companies is increasingly challenging but also more and more relevant in the current cross-disciplinary and complex technological environment. Existing approaches for operationalizing company knowledge are based on patent data and analyzing patent classifications. These approaches have, however, significant limitations. In this study, knowledge depth and breadth is studied using full-text patent data from seven large telecommunication companies totaling 157,718 patents. The data was analyzed with Latent Dirichlet Allocation, an unsupervised learning method. The results are quantified using a technological diversity metric, showing temporal changes in companies knowledge. The result show how the operationalization of company knowledge is independent of patent count and that companies have their specific trajectory of knowledge development. The approach offers a novel method of analyzing the knowledge trajectory of a company, compared to existing patent classification based methods.

KW - patents

KW - companies

KW - portfolios

KW - communications technology

KW - unsupervised learning

KW - trajectory

KW - time series analysis

UR - http://www.scopus.com/inward/record.url?scp=85028575610&partnerID=8YFLogxK

U2 - 10.1109/TEMSCON.2017.7998354

DO - 10.1109/TEMSCON.2017.7998354

M3 - Conference article in proceedings

SN - 978-1-5090-1115-5

SP - 55

EP - 60

BT - 2017 IEEE Technology and Engineering Management Society Conference, TEMSCON 2017

PB - Institute of Electrical and Electronic Engineers IEEE

ER -

Suominen A. Topic modelling approach to knowledge depth and breadth: Analyzing trajectories of technological knowledge. In 2017 IEEE Technology and Engineering Management Society Conference, TEMSCON 2017. Institute of Electrical and Electronic Engineers IEEE. 2017. p. 55-60. 7998354 https://doi.org/10.1109/TEMSCON.2017.7998354