• Journal of the Korean Society for Library and Information Science
• /
• v.56 no.4
• /
• pp.515-536
• /
• 2022

The purpose of this study is to understand the content characteristics in YouTube videos of the National Archives of Korea. For this purpose, keywords, video data, and viewer responses were collected for 324 videos posted by the National Archives of Korea for five years since April, 2017. Social network analysis, topic modeling, and content analysis were performed. Based on this, the main keywords leading the YouTube videos of the National Archives of Korea, 7 major topics and 20 sub-topics were identified. The characteristics of the YouTube videos and keywords network were studies. In addition, video characteristics were analyzed as external characteristics, video editing and delivery methods, and content characters. The study found that the YouTube channel of the National Archives of Korea has been posting the videos related to various topics such as places, history, and events as well as the basic functions of the archives to induce viewers' interest in the archives. The study also identified the areas that needed to be improved such as low response from viewers, lack of content that could interest viewers, and lack of channel operation to interact or communicate with viewers. Finally, the study was concluded with a proposal to spread the videos of the National Archives of Korea to more users.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2009.05a
• /
• pp.129-132
• /
• 2009

본 논문은 오픈 API를 이용하여 다국어 정보검색 시스템을 모델링하는 방법론을 제시한다. 웹 2.0이 대두되면서 웹 2.0의 개념을 활용한 기술들이 발달하고 있는데, 그 중 한 기술이 오픈 API이다. 기업에서 개발한 새로운 서비스나 기능, 데이터 등을 API로 공개함으로써 사용자들이 공개된 API를 이용하여 새로운 서비스를 쉽게 개발할 수 있게 되었다. 본 연구에서는 구글, 플리커, 유튜브, 네이버, 다음 등의 사이트에서 제공하는 오픈 API를 이용하여, 다국어 정보 검색 시스템을 구현하였다. 구글 번역 API를 이용하여 한국어 질의어를 검색 대상 언어(영어, 일본어, 중국어 등)로 번역한 후, 소설 웹 사이트(플리커, 유튜브, 다음, 네이버 등)의 정보를 검색하고, 검색된 결과 내 텍스트를 다시 한국어로 번역한 후, 통합된 검색 결과를 사용자에게 보여준다.

• Journal of Fashion Business
• /
• v.27 no.4
• /
• pp.50-66
• /
• 2023

The purpose of this study was to examine the word distribution and topic distribution of slow fashion appearing on YouTube in detail and identify the characteristics and aspects related to fashion design through big data analysis and content analysis methods. The specific research results were as follows. First, in the results of the word distribution analysis, "item" appeared the most, 203 times. Also, "one-piece" was a point to pay attention to, as the item had the highest frequency. Second, a total of 5 topics were defined in the topic distribution analysis: topic 1 was "vintage products," topic 2 was "fashion items," topic 3 was "eco-friendly," topic 4 was "life quality emphasis," and topic 5 was "prudent consumption." Third, looking at the relationship between word distribution and topic distribution above, Korean slow fashion on YouTube was actively selecting related design elements that express vintage images in clothing life regardless of trends. In addition, there was a tendency to pursue various basic and high-quality items. Other than those findings, basic items tended to be reinterpreted in various ways through styling methods matched to the vintage image. Lastly, the tendency of slow and small-volume production appeared to emphasize handicrafts and the cultural values of fashion products.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.8
• /
• pp.189-198
• /
• 2019

This study aims to make meaning of the reactions of the Korean people through the text mining of comments on videos of the December 2018 MMA performance of intro on YouTube. For this, comments on 15 YouTube videos were collected over the past 10 months. With the collected data, a total of 5,135 comments were analyzed through crawling using the Python and BeautifulSoup programs, data was refined over a total of 3 sessions, and a final total of 5,080 comments were used as analysis material. A mining technique was used for data analysis and the process of refinement, analysis, and visualization was achieved using the Textom program. Research results showed that keyword analysis showed the keywords of 'performance', 'Korea', 'video', 'top', 'cool', 'dance', 'idol', 'legend', 'love', and 'gratitude' in that order and keywords such as 'patriotism' and 'Olympics' also appeared frequently. N-gram analysis showed that comments with contexts such as 'a top performance that will remain a legend among Korean idol performances', and 'an idol performance that displayed the traditional culture of Korea' were in higher ranks. Based on such keyword analysis results, topic modeling was applied and 5 top keywords were extracted from a total of 5 topics. Analysis results of topic contents and distribution showed that topics in the comments of this performance's videos largely consisted of the 3 reactions of 'high praise regarding the stage performance', 'affection towards the fusion and artistic sublimation of Korean traditional dance', and 'gratitude towards the uploading of cool dance videos'

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.11
• /
• pp.1571-1576
• /
• 2022

This study aims to analyze the interest of modern people in non-face-to-face medical counseling in the medical industrys. Big data was collected on two social platforms, 지식인, a platform that allows experts to receive medical counseling, and YouTube. In addition to the top five keywords of telephone counseling, "internal medicine", "general medicine", "department of neurology", "department of mental health", and "pediatrics", a data set was built from each platform with a total of eight search terms: "specialist", "medical counseling", and "health information". Afterwards, pre-processing processes such as morpheme classification, disease extraction, and normalization were performed based on the crawled data. Data was visualized with word clouds, broken line graphs, quarterly graphs, and bar graphs by disease frequency based on word frequency. An emotional classification model was constructed only for YouTube data, and the performance of GRU and BERT-based models was compared.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.1-28
• /
• 2022

In recent years, many Internet giants have begun providing their own content services, which attract online users by offering personalized services based on artificial intelligence technologies. This study investigates the role of two firms' content services within the firms' online service network. We examine the role of Naver Webtoon, which can be characterized as a professional-generated content, within Naver's service portfolio, and that of Google YouTube, which can be characterized as a user-generated content, within Google's service portfolio. Using survey data on viewers' use of the two services, we analyze a valued directed service network, where a node denotes an online service and a relationship between two nodes denotes a sequential use of two services. We found that both Webtoon and YouTube show higher out-degree centrality than in-degree centrality, which implies these content services are more likely to be starting services rather than arriving services within the firms' interactive network. The gap between the out-degree and in-degree centrality of YouTube is much smaller than that of Webtoon. The high centrality of YouTube, a user-generated content service, within the Google service network shows that YouTube's initial role of providing specific-content videos (e.g., entertainment) has expanded into a general search service for users.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.1-13
• /
• 2023

The widespread adoption of smartphones and advancements in internet technology have notably shifted content consumption habits toward video. This research aims to dissect the nature of videos posted on YouTube, the global video-sharing platform, to understand the characteristics of both produced and preferred content. For this study, dance was chosen as a specific subject from a variety of video categories. Data on YouTube videos associated with the term "dance" was compiled over three years, from 2019 to 2021. The investigation revealed a clear distinction between the types of dance videos frequently uploaded to YouTube and those that receive a high number of views. The empirical analysis of this study indicates a viewer preference for vlogs that provide insights into the daily lives of dance students, as well as for purpose-driven videos, such as those highlighting dance exam preparations or school dance events. Notably, the vlogs that attract the most attention are typically created by dance students at the college or secondary school level, rather than by professionals. Although the study was focused on dance, its methodologies can be applied to different subjects. These insights are expected to contribute to the development of a recommendation system that aids content creators in effectively targeting their productions.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.667-668
• /
• 2023

IT 기술의 발달로 인해 뉴스를 제공하는 플랫폼들이 다양해 졌고 최근 해외 인터뷰 영상, 해외 뉴스를 Youtube Shorts형태로 제작하여 화자의 의도와는 다른 자막을 달며 가짜 뉴스가 생성되는 문제가 대두되고 있다. 이에 본 논문에서는 Sentence-BERT를 활용한 YouTube 가짜 뉴스 탐지 시스템을 제안한다. 제안하는 시스템은 Python 라이브러리를 사용해 유튜브 영상에서 음성과 영상 데이터를 분류하고 분류된 영상 데이터는 EasyOCR을 사용해 자막 데이터를 텍스트로 추출 후 Sentence-BERT를 활용해 문자 유사도를 분석한다. 분석결과 음성 데이터와 영상 자막 데이터가 일치한 경우 일치하지 않은 경우보다 약 62% 더 높은 문장 유사도를 보였다.

• Informatization Policy
• /
• v.31 no.1
• /
• pp.3-31
• /
• 2024

This study aimed to examine public concerns in South Korea considering the country's unique context, triggered by the advent of generative artificial intelligence such as ChatGPT. To achieve this, comments from 102 YouTube video news related to ethical issues were collected using a Python scraper, and morphological analysis and preprocessing were carried out using Textom on 15,735 comments. These comments were then analyzed using a Correlated Topic Model (CTM). The analysis identified six primary topics within the comments: "Legal and Ethical Considerations"; "Intellectual Property and Technology"; "Technological Advancement and the Future of Humanity"; "Potential of AI in Information Processing"; "Emotional Intelligence and Ethical Regulations in AI"; and "Human Imitation."Structuring these topics based on a correlation coefficient value of over 10% revealed 3 main categories: "Legal and Ethical Considerations"; "Issues Related to Data Generation by ChatGPT (Intellectual Property and Technology, Potential of AI in Information Processing, and Human Imitation)"; and "Fear for the Future of Humanity (Technological Advancement and the Future of Humanity, Emotional Intelligence, and Ethical Regulations in AI)."The study confirmed the coexistence of various concerns along with the growing interest in generative AI like ChatGPT, including worries specific to the historical and social context of South Korea. These findings suggest the need for national-level efforts to ensure data fairness.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.611-612
• /
• 2020

최근 유튜브, 네이버와 같은 플랫폼 사업자들은 다양하고 많은 동영상확보를 위해 최대한 시간을 적게 들이고 좋은 퀄리티의 영상을 자동으로 생성해주는 어플리케이션을 개발하는데 AI 기술을 적극적으로 사용하고 있다. 가장 주도적으로 진행하는 곳은 IBM 의 왓슨의 인지하이라이트 기술이다. 관중의 함성소리와 스포츠특성 데이터들을 활용하여 하이라이트 부분의 영상만 자동 생성하고 있다. 하지만 현재까지의 기술은 인간의 감성을 자극하는 스토리 전개방식의 자동영상 생성에 있어서는 부족한 부분이 많이 존재한다.이 에 본 논문은 영화의 클라이맥스 부분의 영상편집방식을 분석하여 이에 대한 장르별 샷 사이즈 변화패턴을 시각화한 후, 장르간 편집 차이점을 패턴화한 템플릿을 구축하여 사용자의 이미지 데이터들을 장르별 클라이맥스 패턴의 특성에 맞게 추천하여 짧은 영상을 자동 생성하는 어플리케이션을 개발하였다. 향후 본 연구는 1 인 미디어 산업 및 사이버교육 분야에서 가장 많이 소요되는 영상편집 시간을 단축하는데 큰 효율이 있을 것이라 기대한다.