Abstract

Indonesia needs a technology development strategy by referring to existing development data. Existing data can be obtained from past patent data. In accelerating the discovery of evolution technology map, techniques are needed to extract patent information to technology clusters. To do this, a combination of the Word2Vec and TF-IDF models is used. Both models are used to calculate similarities among patent documents. 194 Indonesian ICT patent documents were processed in this study. Similar patents are clustered using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. The result is 105 patent clusters, 15 of these clusters were detected as experiencing evolution. This means that many research activities have been done by Indonesian scientists, but only 14.29% of them have shown some evolution. The rest of the 85.71% of the research ended up without further development.

Original languageEnglish
Title of host publicationProceeding - 6th International Conference on Information Technology, Information Systems and Electrical Engineering
Subtitle of host publicationApplying Data Sciences and Artificial Intelligence Technologies for Environmental Sustainability, ICITISEE 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages109-114
Number of pages6
ISBN (Electronic)9798350399615
DOIs
Publication statusPublished - 2022
Event6th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2022 - Virtual, Online, Indonesia
Duration: 13 Dec 202214 Dec 2022

Publication series

NameProceeding - 6th International Conference on Information Technology, Information Systems and Electrical Engineering: Applying Data Sciences and Artificial Intelligence Technologies for Environmental Sustainability, ICITISEE 2022

Conference

Conference6th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2022
Country/TerritoryIndonesia
CityVirtual, Online
Period13/12/2214/12/22

Keywords

  • ICT
  • Indonesian patent documents
  • evolution map

Fingerprint

Dive into the research topics of 'ICT Evolution Map Based on Indonesian Patent Documents Using Text Clustering Analysis'. Together they form a unique fingerprint.

Cite this