• Title/Summary/Keyword: YOUTUBE

Search Result 153, Processing Time 0.029 seconds

Ensemble Machine Learning Model Based YouTube Spam Comment Detection (앙상블 머신러닝 모델 기반 유튜브 스팸 댓글 탐지)

  • Jeong, Min Chul;Lee, Jihyeon;Oh, Hayoung
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.24 no.5
    • /
    • pp.576-583
    • /
    • 2020
  • This paper proposes a technique to determine the spam comments on YouTube, which have recently seen tremendous growth. On YouTube, the spammers appeared to promote their channels or videos in popular videos or leave comments unrelated to the video, as it is possible to monetize through advertising. YouTube is running and operating its own spam blocking system, but still has failed to block them properly and efficiently. Therefore, we examined related studies on YouTube spam comment screening and conducted classification experiments with six different machine learning techniques (Decision tree, Logistic regression, Bernoulli Naive Bayes, Random Forest, Support vector machine with linear kernel, Support vector machine with Gaussian kernel) and ensemble model combining these techniques in the comment data from popular music videos - Psy, Katy Perry, LMFAO, Eminem and Shakira.

Intention to Work as a YouTube Creator: Focusing on Generation Z's Occupational Values (유튜브 크리에이터 직업 선택 의향: Z세대 직업 가치관을 중심으로)

  • Cho, Ju-Yeon;Jang, Seong-Ho
    • The Journal of the Korea Contents Association
    • /
    • v.21 no.3
    • /
    • pp.752-760
    • /
    • 2021
  • The present study aimed to identify predictors of Youtube creator's Willingness to work as a profession. This work is notable, given its prevalence in preference as an occupation due to the development of information and communication technology. In the present work, a survey study was utilized and respondents' perception of job values, interest, self-esteem as well as willingness to work were measured. The results from a multiple regression analysis indicate that, realistic type (-), artistic type (+), corporate type (+) job value and job interest were significantly predictive of willingness to work. This study discussed implications including the need to establish career support services for YouTube creators as a profession and further for differentiated approaches based on job values or individual tendencies. The result from the current work is important, in that this study identified the willingness and influential factors of YouTube creators from a professional perspective, reflecting the recent growing interest in YouTube creators.

The Effect of Quasi-social Interaction on Intention of behavior of YouTube beauty content users (유튜브 뷰티콘텐츠 이용자의 준사회적 상호작용이 행동의도에 미치는 영향)

  • Park, SuJeong;Yang, EunJin
    • Journal of Digital Convergence
    • /
    • v.19 no.2
    • /
    • pp.457-462
    • /
    • 2021
  • YouTube has established itself as a major media platform. Businesses give more attention to YouTube's influence as marketing using the platform demonstrates positive effects. Accordingly, this study aims to look into how the quasi-social interaction of the users of beauty content on YouTube affect purchase behavior intentions and provide results as basic data for establishing an efficient marketing strategy. Quasi-social interaction exerted significantly positive influence on purchase behavior and purchase intention. This suggests that the stronger the quasi-social interaction becomes, purchase behavior and purchase intention get stronger. Therefore, strategies for facilitating marketing should be devised by increasing efficient quasi-social interaction according to user characteristics.

Integrated Verbal and Nonverbal Sentiment Analysis System for Evaluating Reliability of Video Contents (영상 콘텐츠의 신뢰도 평가를 위한 언어와 비언어 통합 감성 분석 시스템)

  • Shin, Hee Won;Lee, So Jeong;Son, Gyu Jin;Kim, Hye Rin;Kim, Yoonhee
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.10 no.4
    • /
    • pp.153-160
    • /
    • 2021
  • With the advent of the "age of video" due to the simplification of video content production and the convenience of broadcasting channel operation, review videos on various products are drawing attention. We proposes RASIA, an integrated reliability analysis system based on verbal and nonverbal sentiment analysis of review videos. RASIA extracts and quantifies each emotional value obtained through language sentiment analysis and facial analysis of the reviewer in the video. Subsequently, we conduct an integrated reliability analysis of standardized verbal and nonverbal sentimental values. RASIA provide an new objective indicator to evaluate the reliability of the review video.

A Study on the Fashion Design and Style of K-Pop Boy Groups - Focusing on the Music Programs and YouTube Videos of BTS and Seventeen - (K-Pop 보이 그룹의 패션디자인 및 스타일 연구 - 방탄소년단, 세븐틴의 음악 방송 프로그램 및 유튜브 영상을 중심으로 -)

  • WANG, LIANKAI;Kim, Yoon Kyoung;Lee, Kyoung Hee
    • Fashion & Textile Research Journal
    • /
    • v.23 no.6
    • /
    • pp.726-743
    • /
    • 2021
  • This study tried to examine the fashion design and style of representative K-Pop boy groups BTS and SEVENTEEN appearing on music shows. The data collection was conducted on 4 music programs(Inkigayo, Music Bank, Show! Music Core, M COUNTDOWN) and YouTube(www.youtube.com) for each boy who worked for 5 years from January 2016 to December 2020. Result analysis utilized the stage scenes and music videos of the title songs of BTS and Seventeen. As for the fashion design and style characteristics of BTS, it was found that overall, the color, pattern, and decoration of the bottom were minimized, and the style was changed mainly by the top of the denim pants. As for Seventeen's fashion design and style characteristics, it was analyzed that plain simple slacks, bright and modest chromatic colors, and geometric and stylistic patterns with street retro sensibility were relatively emphasized, and natural and romantic images appeared a lot. As a result of examining the differences in fashion design and style characteristics between BTS and Seventeen, significant differences were found in color, tone, color scheme, material type, material combination, detail, trimming, pattern, accessories, and fashion image. Overall, it was found that both groups minimized the use of decorative elements such as patterns, details, and trimmings.

ALS One-stop Support Service Development Study - Korea-Japan Case Study - (루게릭장애인 원스탑지원서비스 개발연구 - 한일사례연구 -)

  • Chong, Hee-Kyong
    • Journal of Korea Entertainment Industry Association
    • /
    • v.14 no.3
    • /
    • pp.443-454
    • /
    • 2020
  • This study aims to develop one-stop support service for the ALS. To achieve the purpose, the cases of Korea and Japan were researched. The data used in the multiple-case study mainly referred to diaries, blogs, social networking sites, Youtube, and interviews of the disabled with ALS disease in Korea and Japan, and analyzed support services of both countries. The result of the study showed that, in the onset stage of ALS disease, a fellow counselor should be assigned by family member or person who experienced the disease from KALSA or other organizations to which a patient belongs. Also, it need a counseling by fellow counselor in the stage of softening disability. And after the gastrointestinal procedure, the number of home visits by visiting nurses should increase, and other services by OT and PT are required. In the stage of wearing a respirator, it needs to train and dispatch volunteers for ALS exclusive activities. And it is necessary to set up a family rest area or a respite service for the mentally and physically exhausted primary caregiver by long-term care. Most of all, these services should be one-stop support with linking step by step, not fragmentary support.

A comparison of the types and characteristics of the purchase channel journey of fashion products in the MZ generation (MZ세대의 패션상품 구매채널여정 유형화와 특징 비교)

  • Lee, Jung-Woo;Kim, Mi Young
    • The Research Journal of the Costume Culture
    • /
    • v.30 no.5
    • /
    • pp.656-674
    • /
    • 2022
  • The purpose of this study is to reveal and compare the differences in the types and characteristics of purchase channel journeys of MZ generation consumers. In this study a survey was conducted on the purchase channel journey of 20 women in the MZ generation using the ethnographic method of in-depth interviews and observations. As a result, three purchase channel journeys were identified: mobile, multi-channel, and offline. These were variously subdivided according to the characteristics of the MZ generations. Gen Z's journey was categorized into types: fashion platform app, Youtube, multi-channel supplement, multi-channel non-planned store visit, offline loyalty store, and impulsive offline store. Gen M's journey was categorized as: an online community bond, portal site, online loyalty store, multi-channel brand involvement, multi-channel efficiency, a multi-channel conversion, offline efficiency and offline task. The difference in mobile journey between generations was found in the time and length of the purchase. Gen M recognized both online and offline search processes to be tiring, while Gen Z enjoyed the search process using the online path. In the offline journey Gen Z began with their own intention to purchase, while Gen M sometimes recognized that purchasing fashion products necessary for work was a cumbersome task.

A Study on the Effects of Caregivers' YouTube Food Content Viewing on their Children's Health Status (주 양육자의 유튜브 음식 콘텐츠 시청이 자녀의 건강 상태에 미치는 영향 연구)

  • Seojeong Yim;Mi Sook Cho;Jieun Oh
    • Journal of the Korean Society of Food Culture
    • /
    • v.38 no.4
    • /
    • pp.217-223
    • /
    • 2023
  • There has been an increase in the viewing of YouTube content among children and adolescents. This, coupled with the popularity of live-streamed video content such as mukbang, where viewers watch the host eat, has raised concerns about media addiction and the indiscriminate imitation of eating behavior. Therefore, there is a need for guidance on the appropriate behavior for viewing YouTube food content to promote healthy eating habits among children. In this study, we aimed to compare the patterns of the main caregivers and their children while viewing media and investigate the impact of viewing YouTube food content on the physical and mental health of the children. The findings suggest that active YouTube food content viewing by the main caregivers may reduce imitative behaviors due to passive media consumption by their children. This study provides valuable insights by comparing and analyzing the YouTube content viewing of the main caregivers and their children. The results can be used as a basis for the development of lifestyle-centered guidelines for children. However, it is important to note that this study was conducted during the coronavirus disease (COVID-19) pandemic when there was a significant increase in the use of media, which is limitation of the study.

A Study on the Analysis of Policy PR Content Using Digital Platform - Focusing on YouTube Analysis by Five Government Departments (디지털 플랫폼을 이용한 정책 홍보 내용분석 연구 정부 5개 부처의 유튜브 분석을 중심으로)

  • Yu, Hyun-Joong;Jeong, Hyeon Ju;Kim, Won-Han
    • The Journal of the Convergence on Culture Technology
    • /
    • v.9 no.1
    • /
    • pp.595-603
    • /
    • 2023
  • Recently, many public institutions have been conducting promotional activities using digital platforms. Communication methods using digital platforms have a very important meaning in that they can create new values that did not exist before by connecting and sharing information with various users. To this end, we tried to analyze YouTube videos of five government ministries and examine them. As a result of YouTube analysis by government ministries, most of them were mainly used as channels for policy promotion, and many were used as channels for new information. Although the message is delivered through the production of various contents, it was possible to look at cases where the target as a channel for communication was not clear and the purpose was unclear. In order to communicate with the people, it should be used as a channel for communication through content suitable for clear target setting and purpose.

Video Automatic Editing Method and System based on Machine Learning (머신러닝 기반의 영상 자동 편집 방법 및 시스템)

  • Lee, Seung-Hwan;Park, Dea-woo
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2022.05a
    • /
    • pp.235-237
    • /
    • 2022
  • Video content is divided into long-form video content and short-form video content according to the length. Long form video content is created with a length of 15 minutes or longer, and all frames of the captured video are included without editing. Short-form video content can be edited to a shorter length from 1 minute to 15 minutes, and only some frames from the frames of the captured video. Due to the recent growth of the single-person broadcasting market, the demand for short-form video content to increase viewers is increasing. Therefore, there is a need for research on content editing technology for editing and generating short-form video content. This study studies the technology to create short-form videos of main scenes by capturing images, voices, and motions. Short-form videos of key scenes use a pre-trained highlight extraction model through machine learning. An automatic video editing system and method for automatically generating a highlight video is a core technology of short-form video content. Machine learning-based automatic video editing method and system research will contribute to competitive content activities by reducing the effort and cost and time invested by single creators for video editing

  • PDF