정책 분야 텍스트 분석 기반 구축사업

제1장 서론 제1절 정책사전 구축 연구 배경 및 필요성 ············································································3 제2절 연구 목적 ·····················································································································5 제3절 분석방법(정책사전 구축단계) ························································································6 제2장 공적연금 분야 정책사전 구축 과정 제1절 자연어처리 사전 ·········································································································11 1. 키워드에 대한 사전작업 ······································································································11 2. 감정단어 정리 ·····················································································································39 3. TART를 활용한 형태소 분석 수정보완 ···············································································56 4. 공적연금 관련 단어 사전 구축 ···························································································66 제2절 공적연금 분야 정책사전 ·····························································································81 1. 정책구조 ·····························································································································81 2. 정책구조에 대한 자료 코딩(tagging) 설계 ·········································································85 3. 소결 ····································································································································92 4. 환경에 대한 자료 코딩(tagging) 설계 ················································································96 5. 정책 코딩 과정의 요약 및 시각화 ····················································································100 제3절 정책사전 구축 시 “법률용어” 및 “법령상 용어”의 고려 ··········································110 경제⋅인문사회연구회제3장 텍스트 분석 기반 정책 분석 사전 및 환경 구축 제1절 사용자 사전 적용 범위 설계 및 구축 ······································································121 제2절 텍스트 기반 자연어 실시간 분석 모델에서의 사전 설계 ·········································123 제3절 정책 분야 전문 사전 및 분석 모델 구축 ·································································124 제4절 자연어처리를 위한 사전(dictionary) 구성 ·······························································126 제5절 사전(dictionary) 구성 방법 ·····················································································128 제6절 사용자 사전 구축 및 적용 범위 ··············································································138 제7절 수집데이터 대상 사전 적용 및 데이터 처리 프로세스 ·············································139 제4장 결론 결론 ····································································································································143 ￭ 참고문헌 ·····························································································································151 ￭ 부록 1 ·······························································································································154 ￭ 부록 2 ·······························································································································208 ￭ 부록 3 ·······························································································································218표 차례 CF 키워드를 도출한 “연금” 네이버 검색 결과 ·······································································12 분석대상 CF 키워드 분포의 기술통계 ·····················································································12 분석대상 CF 키워드의 상위 100개 ························································································14 CF corpus의 키워드의 동의어 사례 ·······················································································15 형태소 검색 결과 참조 빈도가 낮은 키워드(빈도 수) ······························································20 형태소 검색 과정에서 나타나는 참조빈도 1 키워드 ································································21 최빈 키워드인 “국민” 형태소 검색 결과(발췌) ········································································22 “개혁” 및 “위원회” 형태소 검색 결과와 재분류 작업 ························································…

출처: 국립중앙도서관 서지정보