데이터 마이닝을 활용한 가짜뉴스의 선제적 대응을 위한 연구 : M 온라인 커뮤니티 게시물을 중심으로

• 발행기관: 한국IT서비스학회
• 저자명: 임문영(Munyeong Lim) 박승범(Sungbum Park)
• 간행물 정보: 『한국IT서비스학회지』한국IT서비스학회지 제18권 제1호, 219~234쪽, 전체 16쪽
• 주제분류: 경제경영 > 경영학
• 파일형태: PDF
• 발행일자: 2019.03.30

영문 초록

Fake news threaten democratic elections and causes social conflicts, resulting in major damage. However, the concept of fake news is hard to define, as there is a saying, News is not fake, fake is not news. Fake news, however, has irreversible characteristics that can not be recovered or reversed completely through post-punishment of economic and political benefits. It is also rapidly spreading in the early days. Therefore, it is very important to preemptively detect these types of articles and prevent their blind proliferation. The existing countermeasures are focused on reporting fake news, raising the level of punishment, and the media & academia to determine the authenticity of the news. Researchers are also trying to determine the authenticity by analyzing its contents. Apart from the contents of fake news, determining the behavioral characteristics of the promoters and its qualities can help identify the possibility of having fake news in advance. The online community has a fake news interception and response tradition through its long-standing community-based activities. As a result, I attempted to model the fake news by analyzing the affirmation-denial analysis and posting behavior by securing the web board crawl of the ‘M community’ bulletin board during the 2017 Korean presidential election period. Random forest algorithm deemed significant. The results of this research will help counteract fake news and focus on preemptive blocking through behavioral analysis rather than post-judgment after semantic analysis.

목차

1. 서 론

2. 이론적 배경 및 선행 연구

3. 가짜뉴스의 정책․연구 동향

4. 기술적 연구 동향과 한계

5. 선제적 대응

6. 연구방법 및 분석

7. 모델링과 평가

키워드

Fake News Preempive Measure Misinformation Online Community