메타데이터를 활용한 1960∼2018 〈한국언론학보〉논문 분석 : 다이내믹 토픽 모델링(Dynamic Topic Modeling) 방법을 중심으로
자료요약
이 연구는 〈한국언론학보〉 창간호부터 2018년까지 논문 전집 메타데이터를 활용하여 두 가지 접근으로 학보의 60년을 분석하였다. 우선 기술통계 분석 결과 〈한국언론학보〉의 총 논문 수는 2,048편, 학보논문 저자는 1,276명으로 나타났다. 2001년 이후 누적 논문 수는 2000년 이전과 비교할 때 양적으로 약 3배 증가하였으나 최근 4년간 논문 수가 급감해 학보의 역할에 대한 논의가 필요함을 제안하였다. 학보 논문의 주요 토픽이 60년간 어떠한 진화 패턴으로 나타나는지 알아보기 위해 시계열 데이터 연산 알고리즘인 다이내믹 토픽 모델링(DTM : Dynamic Topic Modeling)으로 분석한 결과 첫째, 연구영역에서는 저널리즘과 온라인 저널리즘, 보도관련 저널리즘이 발생확률이 높은 토픽으로 추출된 반면, 문화연구는 발생확률이 낮게 나타났다. 둘째, 방법론에서는 경험주의 연구와 실증연구가 지배적 토픽으로 나타났고 컴퓨테이셔널 방법론도 증가추세로 나타났다. 셋째, 이론에서는 프레임, 이용과 충족, 의제설정이 주요 토픽으로 추출되었으며 넷째, 메시지연구는 효과 관련 토픽이, 다섯째, 수용자 연구에서는 정치참여, 텔레비전 시청, 청소년 관련 토픽이 지배적으로 나타났다. 마지막으로 연구대상에서는 온라인, 소셜미디어, 인터넷 토론 관련 토픽이 지배적으로 나타나 온라인 관련 연구가 활성화되었음을 알 수 있었다. 이 연구는 내용분석 분류 방법과 달리 메타데이터를 활용해 알고리즘과 기계학습으로 토픽을 추출하고 이를 군집화(clustering)하여 학보 논문의 연구경향 분석방법을 새롭게 제안해 논의했다는데 의의가 있다.
This study analyzed the 60 years of journals, from the first issue to 2018, of the 〈Korean Journal of Journalism & Communication〉 with two approaches using the metadata of the complete edition of academic articles. First, the descriptive statistics indicated that the journal has 1,276 authors and 2,048 articles. From 2001, the number of articles has increased by threefold than before, but has been decreasing for the last four years. Next, we used Dynamic Topic Modeling (DTM) to understand the developing pattern of the topics by creating DTM of the stored articles every five years in six categories. The result of the field of the study showed that journalism, online journalism, and news-related journalism were frequently found while the cultural study was rare. Second, in the methodology, empirical study was the dominant topics over time and the computational methodology was increasingly used. Third, frame, usage and gratification, and agenda setting theory were extracted as the main theoretical topics, and fourth, in the message study, the effect related topics were dominant. Fifth, in the audience study, political participation, television viewing and teenager-related topics were extracted. Lastly, in the research subject, online, social media, and internet discussion were actively discussed topics, which indicates that this journal was enthusiastic to the online-related research. This study is notable as it suggests a new methodology to analyze the study trend of journal articles by clustering the extracted topics from an algorithm using metadata and machine learning.
This study analyzed the 60 years of journals, from the first issue to 2018, of the 〈Korean Journal of Journalism & Communication〉 with two approaches using the metadata of the complete edition of academic articles. First, the descriptive statistics indicated that the journal has 1,276 authors and 2,048 articles. From 2001, the number of articles has increased by threefold than before, but has been decreasing for the last four years. Next, we used Dynamic Topic Modeling (DTM) to understand the developing pattern of the topics by creating DTM of the stored articles every five years in six categories. The result of the field of the study showed that journalism, online journalism, and news-related journalism were frequently found while the cultural study was rare. Second, in the methodology, empirical study was the dominant topics over time and the computational methodology was increasingly used. Third, frame, usage and gratification, and agenda setting theory were extracted as the main theoretical topics, and fourth, in the message study, the effect related topics were dominant. Fifth, in the audience study, political participation, television viewing and teenager-related topics were extracted. Lastly, in the research subject, online, social media, and internet discussion were actively discussed topics, which indicates that this journal was enthusiastic to the online-related research. This study is notable as it suggests a new methodology to analyze the study trend of journal articles by clustering the extracted topics from an algorithm using metadata and machine learning.
목차
1. 들어가며
2. 우리나라 언론학 연구
3. 메타분석과 확률적 토픽 모델(Probabilistic Topic Models)
4. 연구방법 및 연구의 틀
5. 〈한국언론학보〉논문 계량분석
6. 다이내믹 토픽 모델링 분석 결과 : 〈한국언론학보〉논문의 주요 토픽 분석
7. 결론 및 논의
2. 우리나라 언론학 연구
3. 메타분석과 확률적 토픽 모델(Probabilistic Topic Models)
4. 연구방법 및 연구의 틀
5. 〈한국언론학보〉논문 계량분석
6. 다이내믹 토픽 모델링 분석 결과 : 〈한국언론학보〉논문의 주요 토픽 분석
7. 결론 및 논의
#한국언론학보 #다이내믹 토픽 모델링 #확률적 토픽 모델 #메타데이터 #시계열데이터 #Korean Journal of Journalism & # Communication Studies #Dynamic Topic Modeling #Probabilistic Topic Models #metadata #sequential data