상세정보
학술대회
TASIS: Trend Analysis System for International Standards
- 발행일
- 201711
- 출처
- ITU Kaleidoscope Academic Conference 2017, pp.171-178
- 협약과제
- 17HE2400, 빅데이터 상호운용성 지원 표준 개발, 이강찬
- 초록
- Recently, text mining has risen as an advanced technology that analyzes meaningful trends and topics in document collections. Despite its increasing use in various research areas, there have not been previous studies using document collections of international standards. In this paper, we propose the Trend Analysis System for International Standards (TASIS), which automatically performs topic modeling and trend analysis on document collections of the International Telecommunication Union Telecommunication Standardization Sector (ITU-T) Recommendations, based on a latent dirichlet allocation (LDA) algorithm. For providing Web services, the TASIS performs topic modeling by exploiting user-defined parameters, such as the number of topics and iterations, and the results show a list of the documents that each keyword in the topic is included in. The TASIS also describes a TreeMap with the size of the extracted topic as a graphical expression for easier understanding.
- KSP 제안 키워드
- ITU-T, International Telecommunication Union(ITU), International standard, Latent dirichlet allocation (lda), Topic Modeling, Trend analysis, User-defined, WEB SERVICES, advanced technology, analysis system, document collections