텍스트 분석 기반의 개인정보 보호법에 관한 사회적 이슈 연구

This study aimed to identify social issues through text analysis by crawling news articles related to the revision of the Personal Information Protection Act. First, we selected the headlines of the news article and extracted 100 highly influential features using TFIDF and chi-square statistics. Through this, only sentences containing 100 characteristics were extracted for each group and analysis at the sentence level was conducted. Then it followed by LDA topic modeling and network analysis based on keyword. The results showed similar trends in the LDA topic modeling and network analysis based on keyword. This study has academic significance in that it uses LDA topic modeling and network analysis with differentiation from previous research related to the Personal Information Protection Act based on text analysis. In addition, the results of this study are thought to be timely analysis in that we identified social issues before the revision of the Personal Information Protection Act was implemented and could be used as basic data.