RISS 학술연구정보서비스

검색

인기 검색어

    다국어 입력

    http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

    변환된 중국어를 복사하여 사용하시면 됩니다.

    예시)
    • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
    • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
    닫기

    뉴스 헤드라인 감성분석을 이용한 코로나 정책 평가

    한글로보기

    https://www.riss.kr/link?id=T16841372

    • 0

      상세조회
    • 0

      다운로드
    서지정보 열기
    • 내보내기
    • 내책장담기
    • 공유하기
      • URL 복사
    • 오류접수
    인용문이 복사되었습니다.

    부가정보

    국문 초록 (Abstract) kakao i 다국어 번역

    과학기술의 발전에 따라 다양한 영역에서 AI가 급격하게 진화하고 있다. 호텔 룸서비스를 로봇이 가져다주는 등, 어느새 우리 생활에 녹아들었다. 이 중 머신러닝은 현재 대부분이 오픈소스일 뿐만 아니라 다양한 툴과 패키지로 사용하기가 간단해져 개인도 가정용 PC로 머신러닝을 할 수 있다. 이러한 머신러닝을 이용해 코로나 정책에 대한 언론의 평가를 분석하고, 후에 주어지는 정보에도 같은 방법으로 예측을 진행하는 모델을 제작해 보고자 한다.
    본 논문에서는 웹에서 뉴스 데이터 중, 헤드라인 만을 추출하여 데이터셋으로 만들 것이다. 이후 정책집행론적 관점과 현실적인 관점에서 감성사전을 구축하고 텍스트 마이닝의 기법인 분류와 형태소 분석, 라벨링의 과정을 거친다. 감성분석을 진행한 후, 새로운 뉴스 기사에 대해 감성극성을 예측하는 모델을 제작하고 신뢰도를 평가한다. 위와 같은 과정을 통해, 결론적으로 코로나 사태에 대응한 우리 정부의 정책을 여론이 어떻게 평가하는지 정확하게 파악하고, 더 나아가 새로운 데이터에 관해서도 극성을 예측하는 모델을 만들어 앞으로의 상황에 대비한다.
    번역하기

    과학기술의 발전에 따라 다양한 영역에서 AI가 급격하게 진화하고 있다. 호텔 룸서비스를 로봇이 가져다주는 등, 어느새 우리 생활에 녹아들었다. 이 중 머신러닝은 현재 대부분이 오픈소스...

    과학기술의 발전에 따라 다양한 영역에서 AI가 급격하게 진화하고 있다. 호텔 룸서비스를 로봇이 가져다주는 등, 어느새 우리 생활에 녹아들었다. 이 중 머신러닝은 현재 대부분이 오픈소스일 뿐만 아니라 다양한 툴과 패키지로 사용하기가 간단해져 개인도 가정용 PC로 머신러닝을 할 수 있다. 이러한 머신러닝을 이용해 코로나 정책에 대한 언론의 평가를 분석하고, 후에 주어지는 정보에도 같은 방법으로 예측을 진행하는 모델을 제작해 보고자 한다.
    본 논문에서는 웹에서 뉴스 데이터 중, 헤드라인 만을 추출하여 데이터셋으로 만들 것이다. 이후 정책집행론적 관점과 현실적인 관점에서 감성사전을 구축하고 텍스트 마이닝의 기법인 분류와 형태소 분석, 라벨링의 과정을 거친다. 감성분석을 진행한 후, 새로운 뉴스 기사에 대해 감성극성을 예측하는 모델을 제작하고 신뢰도를 평가한다. 위와 같은 과정을 통해, 결론적으로 코로나 사태에 대응한 우리 정부의 정책을 여론이 어떻게 평가하는지 정확하게 파악하고, 더 나아가 새로운 데이터에 관해서도 극성을 예측하는 모델을 만들어 앞으로의 상황에 대비한다.

    더보기

    목차 (Table of Contents)

    • 제1장 서 론 ································································· 1
    • 1. 연구의 배경 및 목적 ···································································· 1
    • 2. 선행 연구 ················································································· 2
    • 3. 논문의 구성 ·············································································· 4
    • 제1장 서 론 ································································· 1
    • 1. 연구의 배경 및 목적 ···································································· 1
    • 2. 선행 연구 ················································································· 2
    • 3. 논문의 구성 ·············································································· 4
    • 제2장 이론적 배경 ······························································· 5
    • 1. 정책집행론 ················································································ 5
    • 2. 텍스트 마이닝 ············································································ 6
    • 3. 머신러닝 ················································································· 11
    • 제3장. 연구 방법 ································································ 13
    • 1. 연구 데이터 ············································································· 14
    • 2. 연구 내용 ················································································ 16
    • 제4장. 실험 결과 ·························································· 23
    • 1. 실험 과정 분석 ········································································· 23
    • 2. 실험 결과 ················································································ 24
    • 제5장. 결론 ······································································ 27
    • 1. 연구의 함의 ············································································· 28
    • 2. 연구의 한계와 시사점 ································································· 29
    • 3. 결론 ······················································································ 30
    • 참 고 문 헌 ················································································ 31
    • ABSTRACT ··············································································· 33
    더보기

    분석정보

    View

    상세정보조회

    0

    Usage

    원문다운로드

    0

    대출신청

    0

    복사신청

    0

    EDDS신청

    0

    동일 주제 내 활용도 TOP

    더보기

    주제

    연도별 연구동향

    연도별 활용동향

    연관논문

    연구자 네트워크맵

    공동연구자 (7)

    유사연구자 (20) 활용도상위20명

    해외이동버튼