• 제목/요약/키워드: research topic

검색결과 2,385건 처리시간 0.04초

토픽모델을 활용한 명문대 재학생의 학벌에 관한 인식 분석 (A Prestigious University Students' Perceptions of their Educational Attainment by a Topic model)

  • 정영선;이승연
    • 문화기술의 융합
    • /
    • 제10권3호
    • /
    • pp.503-512
    • /
    • 2024
  • 이 연구는 한국 사회에서 명문대로 분류되는 한 대학의 학생이 작성한 학벌에 대한 글쓰기 과제를 분석하여 이들이 가진 학벌에 대한 인식을 확인하고 내재한 의미를 분류한 연구이다. 분석에서 활용한 방법은 토픽 모델 중 잠재 디리클레 할당 방법으로 총 172편의 문서를 분석한 후 각 토픽에서 빈출한 키워드가 자주 등장하는 문서를 중심으로 학생의 인식을 탐색하였다. 분석 결과 도출한 토픽은 학벌의 순기능(토픽 1), 양날의 검(토픽 2), 권력공동체(토픽 3), 승리의 징표(토픽 4), 학벌의 역기능(토픽 5)의 다섯 가지이다. 각 토픽에서 가장 빈번하게 제시되는 단어를 정리하면 다음과 같다. 토픽 1에서는 '개인', '지위', '수단'이, 토픽 2는 '정의(定義)', '학교', '의미'가, 토픽 3은 '사람', '출신', '권력'이, 토픽 4는 '대학(교)', '능력', '노력'이, 토픽 5는 '학력', '우리나라', '출신'이었다. 이상의 분석을 통해 우리는 명문대 학생이 학벌을 논할 때 계급과 학벌 공동체, 사회와의 관련성을 통하여 계급재생산을 고려하지만 인종 및 민족와 같이 학벌에 영향을 미치는 기타 요인에 대하여는 크게 관심을 두지 않고 있음을 확인하였다. 앞으로의 관련 강의에서 보다 다양한 요인과 학벌의 관련성을 다룰 필요가 있다.

Generative probabilistic model with Dirichlet prior distribution for similarity analysis of research topic

  • Milyahilu, John;Kim, Jong Nam
    • 한국멀티미디어학회논문지
    • /
    • 제23권4호
    • /
    • pp.595-602
    • /
    • 2020
  • We propose a generative probabilistic model with Dirichlet prior distribution for topic modeling and text similarity analysis. It assigns a topic and calculates text correlation between documents within a corpus. It also provides posterior probabilities that are assigned to each topic of a document based on the prior distribution in the corpus. We then present a Gibbs sampling algorithm for inference about the posterior distribution and compute text correlation among 50 abstracts from the papers published by IEEE. We also conduct a supervised learning to set a benchmark that justifies the performance of the LDA (Latent Dirichlet Allocation). The experiments show that the accuracy for topic assignment to a certain document is 76% for LDA. The results for supervised learning show the accuracy of 61%, the precision of 93% and the f1-score of 96%. A discussion for experimental results indicates a thorough justification based on probabilities, distributions, evaluation metrics and correlation coefficients with respect to topic assignment.

Research on the Movie Reviews Regarded as Unsuccessful in Box Office Outcomes in Korea: Based on Big Data Posted on Naver Movie Portal

  • Jeon, Ho-Seong
    • 아태비즈니스연구
    • /
    • 제12권3호
    • /
    • pp.51-69
    • /
    • 2021
  • Purpose - Based on literature studies of movie reviews and movie ratings, this study raised two research questions on the contents of online word of mouth and the number of movie screens as mediator variables. Research question 1 wanted to figure out which topics of word groups had a positive or negative impact on movie ratings. Research question 2 tried to identify the role of the number of movie screens between movie ratings and box office outcomes. Design/methodology/approach - Through R program, this study collected about 82,000 movie reviews and movie ratings posted on Naver's movie website to examine the role of online word of mouths and movie screen counts in 10 movies that were considered commercially unsuccessful with fewer than 2 million viewers despite securing about 1,000 movie screens. To confirm research question 1, topic modeling, a text mining technique, was conducted on movie reviews. In addition, this study linked the movie ratings posted on Naver with information of KOBIS by date, to identify the research question 2. Findings - Through topic modeling, 5 topics were identified. Topics found in this study were largely organized into two groups, the content of the movie (topic 1, 2, 3) and the evaluation of the movie (topics 4, 5). When analyzing the relationship between movie reviews and movie ratings with 5 mediators identified in topic modeling to probe research question 1, the topic word groups related to topic 2, 3 and 5 appeared having a negative effect on the netizen's movie ratings. In addition, by connecting two secondary data by date, analysis for research question 2 was implemented. The outcomes showed that the causal relationship between movie ratings and audience numbers was mediated by the number of movie screens. Research implications or Originality - The results suggested that the information presented in text format was harder to quantify than the information provided in scores, but if content information could be digitalized through text mining techniques, it could become variable and be analyzed to identify causality with other variables. The outcomes in research question 2 showed that movie ratings had a direct impact on the number of viewers, but also had indirect effects through changes in the number of movie screens. An interesting point is that the direct effect of movie ratings on the number of viewers is found in most American films released in Korea.

LDA를 이용한 국제지적연구의 주제와 추세확인에 관한 연구: 특히 FIG Peer Review Journal을 중심으로 (A Study on Identifying Topics and Trends in International Cadastral Research Using LDA: With Special Reference to the FIG Peer Review Journal)

  • 김윤기
    • 지적과 국토정보
    • /
    • 제48권1호
    • /
    • pp.15-33
    • /
    • 2018
  • 본 연구의 주된 목적은 LDA를 이용하여 국제지적연구의 주제와 연구추세를 확인하는 것이었다. 이러한 연구목적을 달성하기 위해 나는 LDA와 국제지적연구에 관한 선행연구를 검토하였고 이를 기반으로 4 개의 연구 질문을 설정하였다. 이러한 연구 질문에 답을 구하기 위해 나는 FIG Peer Review Journal에 2008년 1월1일 부터 2017년 10월 31일 사이에 발표된 370편의 논문들을 LDA를 이용하여 분석하였다. 분석의 결과 나는 국제지적연구에 12개의 주요 주제가 존재하고 있음을 확인하였다. 그리고 이러한 주제 중에 가장 영향력 있는 주제는 topic 2 (지적정보시스템)로 확인되었으며 또한 topic 5 (토지개발과 토지행정)도 전체 문서에서 중요한 역할을 수행하고 있는 주제로 파악되었다. 이두 주제는 지난 10년 동안 추세선이 매우 활발하게 움직인 가장 인기 있는 주제들로서 앞으로의 지적연구에서도 주도적인 역할을 수행할 것이 틀림없다.

대한예방한의학회지 게재논문의 경향성에 대한 연구 - 창간호(1997년)로부터 2010년까지 - (The Trend of Published Articles to the Korean Journal of Oriental Preventive Medicine - From 1997 to 2010 -)

  • 박해모
    • 대한예방한의학회지
    • /
    • 제15권1호
    • /
    • pp.17-27
    • /
    • 2011
  • Objective : The purpose of this study was to identify the trend of research in the Korean Journal of Oriental Preventive Medicine and to suggest future perspective for oriental preventive medicine research. Method : The contents of 344 articles published in this journal was reviewed from its beginning year 1997 to year 2010. Result : The number of articles was increased as times go on. An analysis of the research design showed, experimental research (in vivo or in vitro) was 36.9%, survey research was 26.5%, review was 20.1%. In the major classifications of topics published, health management 28.5%, oriental medicine effectiveness 25.3%, herbal safety and toxicity 13.1%, and environmental and occupational medicine 9.0% respectively. Conclusion : There has been a lack of health preservation(Yang-saeng) topic, epidemiology and health statistics topic. Further research need qualitative study and each subjects of oriental preventive medicine.

잠재디리클레할당을 이용한 한국학술지인용색인의 풍력에너지 문헌검토 (Review of Wind Energy Publications in Korea Citation Index using Latent Dirichlet Allocation)

  • 김현구;이제현;오명찬
    • 신재생에너지
    • /
    • 제16권4호
    • /
    • pp.33-40
    • /
    • 2020
  • The research topics of more than 1,900 wind energy papers registered in the Korean Journal Citation Index (KCI) were modeled into 25 topics using latent directory allocation (LDA), and their consistency was cross-validated through principal component analysis (PCA) of the document word matrix. Key research topics in the wind energy field were identified as "offshore, wind farm," "blade, design," "generator, voltage, control," 'dynamic, load, noise," and "performance test." As a new method to determine the similarity between research topics in journals, a systematic evaluation method was proposed to analyze the correlation between topics by constructing a journal-topic matrix (JTM) and clustering them based on topic similarity between journals. By evaluating 24 journals that published more than 20 wind energy papers, it was confirmed that they were classified into meaningful clusters of mechanical engineering, electrical engineering, marine engineering, and renewable energy. It is expected that the proposed systematic method can be applied to the evaluation of the specificity of subsequent journals.

토픽 모델링을 이용한 지속가능패션 연구 동향 분석 (Analysis of sustainable fashion research trends using topic modeling)

  • 이하나
    • 복식문화연구
    • /
    • 제29권4호
    • /
    • pp.538-553
    • /
    • 2021
  • As interest in the sustainable fashion industry continues to increase along with climate issues, it is necessary to identify research trends in sustainable fashion and seek new development directions. Therefore, this study aims to analyze research trends on sustainable fashion. For this purpose, related papers were collected from the KCI (Korean Citation Index) and Scopus, and 340 articles were used for the study. The collected data went through data transformation, data preprocessing, topic modeling analysis, core topic derivation, and visualization through a Python algorithm. A total of eight topics were obtained from the comprehensive analysis: consumer clothing consumption behavior and environment, upcycle product development, product types by environmental approach, ESG business activities, materials and material development, process-based approach, lifestyle and consumer experience, and brand strategy. Topics were related to consumption, production, and education of sustainable fashion, respectively. KCI analysis results and Scopus analysis results derived eight topics but showed differences from the comprehensive analysis results. This study provides primary data for exploring various themes of sustainable fashion. It is significant in that the data were analyzed based on probability using a research method that excluded the subjective value of the researcher. It is recommended that follow-up studies be conducted to examine social trends.

2000년 이후 국내 한의학 암 관련 연구 동향 분석 - Latent Dirichlet Allocation 기반 토픽 모델링 및 연관어 네트워크 분석 (Cancer Research Trends in Traditional Korean Medical Journals since 2000 - Topic Modeling Using Latent Dirichlet Allocation and Keyword Network Analysis)

  • 배겨레
    • 대한한방내과학회지
    • /
    • 제43권6호
    • /
    • pp.1075-1088
    • /
    • 2022
  • Objectives: The aim of this study is to analyze cancer research trends in traditional Korean medical journals indexed in the Korea Citation Index since 2000. Methods: Cancer research papers published in traditional Korean medical journals were searched in databases from inception to October 2022. The numbers of publications by journal and by year were descriptively assessed. After natural language processing, topic modeling (based on Latent Dirichlet allocation) and keyword network analysis were conducted. Results: This research trend analysis involved 1,265 papers. Six topics were identified by topic modeling: case reports on symptom management, literature reviews, experiments on apoptosis, herbal extract treatments of breast carcinoma cell lines, anti-proliferative effects of herbal extracts, and anti-tumor effects. Keyword network analysis found that the effects of herbal medicine were assessed in clinical and experimental studies, while acupuncture was mainly mentioned in clinical reports. Conclusions: Cancer research papers in traditional Korean medical journals have contributed to evidence-based medicine. Further experimental studies are needed to elucidate the effects of on different hallmarks of cancer. Rigorous clinical studies are needed to support clinical guidelines.

비정형 텍스트 기반의 토픽 모델링을 이용한 건설 안전사고 동향 분석 (A Study on the Trends of Construction Safety Accident in Unstructured Text Using Topic Modeling)

  • 이상규
    • 한국산학기술학회논문지
    • /
    • 제19권10호
    • /
    • pp.176-182
    • /
    • 2018
  • 본 연구는 건설 안전사고에 대한 트랜드 분석을 위해 LDA(Latent Dirichlet Allocation) 기반의 토픽모델링(Topic Modeling)을 제시하여 분석하고자 한다. 특히, 건설산업의 안전사고를 예방하기 위해 제시되고 있는 기존의 다양한 정형데이터 분석에서 벗어난 비정형 데이터 분석 기반의 토픽 모델링을 통해 건설 안전사고 주요 핵심 키워드의 흐름에 대해 파악이 가능하다. 본 방법론을 적용하기 위해 540개의 건설 안전사고 관련 뉴스데이터를 수집하였다. 이를 기반으로, 10가지 토픽과 각 토픽 내의 10가지 키워드를 통해 주요 이슈를 도출하였고 각 토픽에 대한 2017년 1월부터 2018년 2월까지의 뉴스 데이터를 월별 시계열 분석을 통해 향후 토픽에 관한 이슈를 예측한다. 본 연구를 바탕으로 향후 건설 안전사고의 다양한 이슈를 선제적으로 예측하고 이를 기반으로 건설 안전사고 정책과 연구에 좋은 방향을 제시할 것으로 판단한다.

자아 중심 네트워크 분석과 동적 인용 네트워크를 활용한 토픽모델링 기반 연구동향 분석에 관한 연구 (Combining Ego-centric Network Analysis and Dynamic Citation Network Analysis to Topic Modeling for Characterizing Research Trends)

  • 유소영
    • 정보관리학회지
    • /
    • 제32권1호
    • /
    • pp.153-169
    • /
    • 2015
  • 이 연구에서는 토픽 모델링 결과 해석의 용이성을 위하여, 동적 인용 네트워크를 활용하여 LDA 기반 토픽 모델링의 토픽 수를 설정하고 중복 배치된 주요 키워드를 자아 중심 네트워크 분석을 통해 재배치하여 제시하는 방법을 제안하였다. 'White LED' 두 분야의 논문 데이터를 이용하여 분석한 결과, 동적 인용 네트워크 분석을 통해 형성된 분석대상 문헌집단에 혼잡도에 따른 토픽수를 사용하고 중복 분류된 토픽 내 주요 키워드를 자아중심 네트워크 분석 기법을 적용하여 재배치한 결과가 토픽 간의 중복도가 가장 낮은 것으로 나타났다. 따라서 동적 인용 네트워크 및 자아 중심 네트워크 분석을 적용함으로써 토픽모델링에 의한 분석 결과를 보완하는 다면적인 연구 동향 분석이 가능할 것으로 보인다.