빅데이터의 하위 주제어 의미 분석 연구
Semantic Analysis of The Sub-Thematic Word in Big Data
1
조회
0
다운로드
17
인용
0
참고문헌
키워드
초록
The purpose of this study is to analyze the meaning of the sub-thematic word for big data research. To this end, I investigate thematic words in the KBS News 9, which broadcasted from 2001 through 2011. First, I discuss the meaning and value of the Big Data in the study of language. And I show that the frequency of word is useful qualities as thematic word feature. In order to analyze the data, I selected 20 high-frequency thematic words, using thematic word index of the natural language processing. These present the major issues of our society and the interests of the people. Then I analysis sub-thematic words with sentences that appear within {Mikuk (U.S.)/ Ilbon (Japan)/ Jungkuk (China)} and {Munje (problem)}. Classified according to semantic features, using high-frequency thematic words, semantic relation of thematic words was also discussed. The results show that sub-thematic words have sociolinguistic context, so each sub-thematic words that can be understood in a social context. In conclusion, this study shows the sub-thematic word search is a useful way to understand the data specifically.
Abstract
The purpose of this study is to analyze the meaning of the sub-thematic word for big data research. To this end, I investigate thematic words in the KBS News 9, which broadcasted from 2001 through 2011. First, I discuss the meaning and value of the Big Data in the study of language. And I show that the frequency of word is useful qualities as thematic word feature. In order to analyze the data, I selected 20 high-frequency thematic words, using thematic word index of the natural language processing. These present the major issues of our society and the interests of the people. Then I analysis sub-thematic words with sentences that appear within {Mikuk (U.S.)/ Ilbon (Japan)/ Jungkuk (China)} and {Munje (problem)}. Classified according to semantic features, using high-frequency thematic words, semantic relation of thematic words was also discussed. The results show that sub-thematic words have sociolinguistic context, so each sub-thematic words that can be understood in a social context. In conclusion, this study shows the sub-thematic word search is a useful way to understand the data specifically.
참고문헌 (19)
- "언어학", 2011, 3~38, pp.사단법인 한국언어학회
- 김일환, "공기어를 이용한 사회 문제에 대한 관심의 추이 분석 -2000~2009년 신문기사를 중심으로-", 인문학연구, (21), pp.175~202 (2012), 인문학연구원
- 21세기 세종계획 국어 기초자료 구축 최종보고서, "국립국어원", 국립국어원, ~ (2007)
- 김영택, "자연 언어 처리" (1994), 교학사
- 박건숙, "사람 이름의 의미 자질 연구", 한국어 의미학, 37, pp.161~184 (2012), 한국어의미학회
- 송도규, "인지언어학과 자연언어 자동처리" (1996), 홍릉과학출판사
- 신현숙, "의미로 분류한 현대 한국어 학습 사전" (2000), 한국문화사
- 오길록, "한글공학" (1994), 대영사
- Aitchison, Jean., "WORDS in the MIND" (1987), Basil Blackwell
- Brett Sheppard, "Putting Big Data to Work: Opportunities for Enterprises", GigaOM Structure Big Data 2011 Conference (2011), GigaOM Pro
- Hadoop and MapReduce: Big Data Analytics, "Gartner Report", Gartner, ~ (2011)
- George K. Zipf, "Human Behavior and the Principle of Least Effort" (1949), Addison-Wesley
- George Lakoff, "Thinking points: Communicating our American values and vision" (2006), Farrar, Straus and Giroux
- Grishman, Ralph, "Computational linguistics" (1986), Cambridge University Press
- James Manyika, "Big data: The next frontier for innovation, competition, and productivity" (2011), McKinsey & Company
- Julian Kupiec, "A Trainable Document Summarizer", Proc. of 18th ACM-SIGIR Conference (1995)
- 최기선, "자연언어처리" (1998), 홍릉과학출판사
- Merv Adrian, "It's going mainstream, and it's your next opportunity" (2011), Teradata Corporation
- Miller, George A, "The Science of Words" (1991), Scientific American Library