• Title/Summary/Keyword: YouTube data

Search Result 179, Processing Time 0.027 seconds

Analysis of whether the feeling of relative deprivation is shown in the comments of the Luxury Howl YouTube video - Focusing on modern sentiment analysis using TF-IDF, Word2vec, LDA and LSTM - (명품 하울 유튜브 영상 댓글에 나타난 상대적 박탈감 여부와 특징 분석 - TF-IDF, Word2vec, LDA, LSTM을 이용한 현대인의 감정 분석을 중심으로 -)

  • Choi, Jung Min;Oh, Hayoung
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.25 no.3
    • /
    • pp.355-360
    • /
    • 2021
  • Recently Youtube has been more popular. As many studies show the comparative deprivation of the Social Medeia, this study looks into whether the comparative deprivation is expressed on the YouTube comments. It focuses on the Luxury Haul contents, videos about huge amounts of luxurious products, of which Youtubers'economic feature are demonstrative. The comments of the videos are analyzed with LDA TF-IDF and Word2Vec. Additionally, the comments were classified into positive and negative groups by the LSTM model as well. As a result of the study, even though many comments turned out positive, the negative keywords were indicated related to comparative deprivation. Also it was found that the viewers compared themselves with Youtubers. In particular, some YouTubers are more criticized if they are younger or does not seem to afford the luxurious products themselves. This study suggests that the users express the comparative deprivation on YouTube as well like on the other Social Media.

YouTube Users' Awareness of Online Advertisements and Advertising Regulation Plan (유튜브 이용자들의 온라인광고에 대한 인식 및 광고규제 방안)

  • Kim, Sora
    • The Journal of the Korea Contents Association
    • /
    • v.21 no.9
    • /
    • pp.528-542
    • /
    • 2021
  • This study aims to examine the attitudes toward online advertisement targeting YouTube content users and to present implications for the direction and regulation of personal media broadcasting advertisement. The study used the data from 'Awareness of On-line Ads and Blocking Tools' conducted by the Korea Press Foundation in 2020. For the statistical analysis, correspondent analysis was employed. The main results followed as: women tended to perceive more discomfort about the ads before the start of the content compared to men, and women in twenties perceived the highest discomfort with intermediate advertisement. Second, respondents who watch more YouTube contents tended to accept more ads to use contents for free. Third, respondents who are willing to use the advertisement blocking service were most aware of the inconvenience of advertisements before starting of YouTube contents. Although users are aware of the inconvenience, the use of advertisement blocking service has not yet been found to be generalized. However, the use of ad blocking service is expected to increase gradually. It would be expected that efforts to regulate advertisement to reduce discomfort about advertisement among users are also required.

Computer Vision-Based Car Accident Detection using YOLOv8 (YOLO v8을 활용한 컴퓨터 비전 기반 교통사고 탐지)

  • Marwa Chacha Andrea;Choong Kwon Lee;Yang Sok Kim;Mi Jin Noh;Sang Il Moon;Jae Ho Shin
    • Journal of Korea Society of Industrial Information Systems
    • /
    • v.29 no.1
    • /
    • pp.91-105
    • /
    • 2024
  • Car accidents occur as a result of collisions between vehicles, leading to both vehicle damage and personal and material losses. This study developed a vehicle accident detection model based on 2,550 image frames extracted from car accident videos uploaded to YouTube, captured by CCTV. To preprocess the data, bounding boxes were annotated using roboflow.com, and the dataset was augmented by flipping images at various angles. The You Only Look Once version 8 (YOLOv8) model was employed for training, achieving an average accuracy of 0.954 in accident detection. The proposed model holds practical significance by facilitating prompt alarm transmission in emergency situations. Furthermore, it contributes to the research on developing an effective and efficient mechanism for vehicle accident detection, which can be utilized on devices like smartphones. Future research aims to refine the detection capabilities by integrating additional data including sound.

Research on Consistent Use Intention of Home-training Program on Personal Media Service YouTube Based on Post-Adoption Model (후기수용모델을 적용한 1인 미디어 유튜브 홈 트레이닝의 지속의도 연구)

  • Oh, Jung-Heui;Oh, Jai-Woo;Cho, Kwang-Min
    • Journal of the Korea Convergence Society
    • /
    • v.10 no.2
    • /
    • pp.183-193
    • /
    • 2019
  • This study empirically analyzed the factors affecting satisfaction and consistent use of 'home training' on personal media service YouTube based on Post-Acceptable Model. To this purpose, data were collected from adult men and women with personal media service using experience. As for data analysis, frequency analysis, correlation analysis, confirmatory factor analysis, reliability analysis and path analysis were performed by using SPSS 21.0 and AMOS 21.0. The results of the study were as followed. First, using motivation of YouTube home training had a positive effect on usefulness. Second, health literacy had a positive effect on usefulness. Third, it was found that the expectation confirmation of the home training on personal media service positively influenced usefulness. Forth, expectation confirmation of the home training on personal media service had a positive effect on satisfaction. Fifth, usefulness had a positive effect on satisfaction. Sixth, usefulness had no significant effect on consistent use intention. Seventh, satisfaction had a positive effect on consistent use intention. Behavioral analysis with collective demographic factors and diverse analysis considering the differentiation of the personal media service are suggested for further research.

A Study on Interest Issues Using Social Media New (소셜미디어 뉴스를 이용한 관심 이슈 연구)

  • Kwak, Noh Young;Lee, Moon Bong
    • The Journal of Information Systems
    • /
    • v.32 no.2
    • /
    • pp.177-190
    • /
    • 2023
  • Purpose Recently, as a new business marketing tool, short form content focused on fun and interest has been shared as hashtags. By extracting positive and negative keywords from media audiences through comment analysis of social media news, various stakeholders aim to quickly and easily grasp users' opinions on major news. Design/methodology/approach YouTube videos were searched using the YouTube Data API and the results were collected. Video comments were crawled and implemented as HTML elements, and the collection results were checked on the web page. The collected data consisted of video thumbnails, titles, contents, and comments. Comments were word tokenized with the R program, comparing positive and negative dictionaries, and then quantifying polarity. In addition, social network analysis was conducted using divided positive and negative comments, and the results of centrality analysis and visualization were confirmed. Findings Social media users' opinions on issue news were confirmed by analyzing and visualizing the centrality of keywords through social network analysis by dividing comments into positive and negative. As a result of the analysis, it was found that negative objective reviews had the highest effect on information usefulness. In this way, previous studies have been reaffirmed that online negative information has a strong effect on personal decision-making. Corporate marketers will analyze user comments on social network services (SNS) to detect negative opinions about products or corporate images, which will serve as an opportunity to satisfy customers' needs.

Fake News Detection on Social Media using Video Information: Focused on YouTube (영상정보를 활용한 소셜 미디어상에서의 가짜 뉴스 탐지: 유튜브를 중심으로)

  • Chang, Yoon Ho;Choi, Byoung Gu
    • The Journal of Information Systems
    • /
    • v.32 no.2
    • /
    • pp.87-108
    • /
    • 2023
  • Purpose The main purpose of this study is to improve fake news detection performance by using video information to overcome the limitations of extant text- and image-oriented studies that do not reflect the latest news consumption trend. Design/methodology/approach This study collected video clips and related information including news scripts, speakers' facial expression, and video metadata from YouTube to develop fake news detection model. Based on the collected data, seven combinations of related information (i.e. scripts, video metadata, facial expression, scripts and video metadata, scripts and facial expression, and scripts, video metadata, and facial expression) were used as an input for taining and evaluation. The input data was analyzed using six models such as support vector machine and deep neural network. The area under the curve(AUC) was used to evaluate the performance of classification model. Findings The results showed that the ACU and accuracy values of three features combination (scripts, video metadata, and facial expression) were the highest in logistic regression, naïve bayes, and deep neural network models. This result implied that the fake news detection could be improved by using video information(video metadata and facial expression). Sample size of this study was relatively small. The generalizablity of the results would be enhanced with a larger sample size.

Relevance between Marketing Route of Social Media and Consumer Age Group for Choosing Dental Clinics

  • Lee, Shin-Young;Kwak, Mi-Gyeong;Kim, Mi-Jeong;Song, Jung-Hwa;Lee, Young-Ju;Hong, Hye-Ju;Oh, Sang-Hwan
    • Journal of dental hygiene science
    • /
    • v.21 no.4
    • /
    • pp.260-266
    • /
    • 2021
  • Background: The purpose of the study was to evaluate the relationship and route of dental Social Media marketing by age group and support effective dental marketingy by age group. Methods: A study was conducted on 265 people, aged 20 to 64 years, who lived in Seoul, Gyeonggi area and regularly used one or more of the social media platforms, Naver Band, Facebook, Instagram, KakaoStory, Twitter, or YouTube more than once a day. A 27-question questionnaire survey of approximately 10 minutes was conducted, and the collected data was statistically analyzed using the PASW program, with the significane level set to 0.05. Results: "Introduction of acquaintances" was the most common route to visit the dentist. Regarding the use of social media platforms based on age group, 'Instagram' had the highest frequency among people belonging to the age groups of 20 to 29 years and 30 to 39 years; 'YouTube' had the highest frequency among those aged 40 to 49 years; and 'Naver Band' had the highest frequency among those aged 50 to 65 years. Conclusion: The most frequently used social media by consumers according to age included Facebook, YouTube, and Instagram. However, social media was found to have no significant impact on the choice of dental institutions, as the number of people who visited the dentist through "Introduction of acquaintances" was the highest, and "Introduction of acquaintances" did not have experience accessing the dentist site after dental marketing. If this study could provide customized marketing information for each age group through social media, it is expected that the marketing effect of dental institutions through social media would be maximized in the future.

Analysis of Online Educational Videos for Patients with Radiation Therapy (방사선치료 환자를 위한 온라인 교육 동영상 분석)

  • Kim, Dae-Gun;Jeong, Jae-Hong
    • Journal of radiological science and technology
    • /
    • v.45 no.1
    • /
    • pp.31-39
    • /
    • 2022
  • This study aimed to analyze educational understanding and satisfaction by survey including for the online educational videos by used online platform (YouTube) which provide resolve patient's questions, require attention and treatment information for a patient with radiation therapy. Video viewing analysis was used by YouTube studio. The survey was analyzed general properties (age, academic ability, disease, and watched of no watched videos) and educational understanding and satisfaction for two groups as no watched and watched patients. The views number was 60% at the female higher than 40% at the male. Based on the standard viewing time (hours), the non-subscription rate was 86.7%. The device type mostly used the mobile phone (82.8%). The viewership of educational videos was lower as the age increased and the academic ability decreased in the survey. The educational understanding increased by 22% at watched group as 4.15 point from at no watched group as 3.4 point (p<0.001), and the educational satisfaction increased by 15.8% at watched group as 4.25 point from at no watched group as 3.67 point (p<0.01). The correlation of understanding (r=0.761) and satisfaction (r=0.767) was high for both no watched and watched groups (p<0.01). The online educational videos increased educational understanding and satisfaction for the patient with radiation therapy. Our study could be used references data for improving the quality of medical services.

Deconstruction Characteristics in Fashion Brand YouTube Campaign (패션 브랜드 유튜브 캠페인에 나타난 해체주의적 특성)

  • Youngjae Lee
    • Journal of Fashion Business
    • /
    • v.27 no.3
    • /
    • pp.35-49
    • /
    • 2023
  • The purpose is to derive its aesthetic characteristics by objectifying the visual image of the YouTube campaign into adjectives. As a result, we intend to identify advertising strategies that use them as basic data for setting fashion design concepts. A group of experts in fashion majors watched each of them, wrote adjectives, and collected 75 adjectives. By analyzing the frequency of adjectives, aesthetic characteristics were derived with adjectives recording the upper number of times, and the results were obtained that they had the characteristics of deconstruction. The conclusions of this study are as follows. First, Tamburin's Jenny appeared to be strange, scary, rambling and charming. Among the internal meanings of deconstruction due to spatial, social, and psychological distance from consumers, it can be said that T.P.O's mutual textuality and play of interaction. Second, Gucci Cruise be chosen rural, strange, wild, unharmonious, and difficult, which is a mixture of intertextuality and play of T.P.O. Third, The Excise Gucci Campaign parodies that juxtaposes six films directed by Stanley Kubrick, making them strange, retro, difficult, interesting, and wrong. Deconstructionist de-genre and de-boundary Fourth, Kenzo World is weird, dynamic, wrong, difficult, difficult, and confused, which correspond to T.P.O's interactive textuality, play of the second half, and destruction and decomposition among the external expressions of deconstruction. Fifth, Burberry Hero emphasized the aesthetic value of traditional men, so it was ostensibly wild, free, powerful, sensual, and fantastic. Compared to the lifestyle of men who usually work at work, this corresponds to play of second best.

Analysis of interest in non-face-to-face medical counseling of modern people in the medical industry (의료 산업에 있어 현대인의 비대면 의학 상담에 대한 관심도 분석 기법)

  • Kang, Yooseong;Park, Jong Hoon;Oh, Hayoung;Lee, Se Uk
    • 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.