DOI QR코드

DOI QR Code

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 (Department of Data Science, Sungkyunkwan University) ;
  • Oh, Hayoung (College of Computing & Informatics, Sungkyunkwan University)
  • Received : 2020.09.19
  • Accepted : 2021.01.27
  • Published : 2021.03.31

Abstract

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.

최근 유튜브가 큰 인기를 얻고 있다. 많은 연구에 따르면 소셜 미디어에서 상대적 박탈감이 나타나듯이 본 연구에서는 유튜브에서도 상대적 박탈감이 나타나는지 확인해보고자 한다. 그중에서도 유튜버의 경제적 지위를 잘 드러내는 명품 하울 영상을 중심으로 연구를 진행하였다. 명품 하울이란 많은 양의 명품 제품을 구매하여 보여주는 콘텐츠를 의미한다. LDA, TF-IDF, Word2Vec 기법을 이용하여 유튜브 댓글 분석을 진행하였다. 추가로 LSTM 학습 모델을 기반으로 댓글을 긍정적 그룹과 부정적 그룹으로 분류하였다. 연구 결과에 따르면 다수의 댓글이 긍정적인 의미를 내포하지만, 상대적 박탈감 등을 나타내는 부정적 의미의 키워드를 가진 댓글도 나타났다. 이러한 댓글에서는 자신과 유튜버의 경제적 모습을 비교하는 표현이 등장하였다. 특히 유튜버의 나이가 상대적으로 어리거나 스스로 명품제품을 구매할 능력이 되지 않은 것으로 보이면 상대적 박탈감을 표현하는 댓글이 증가하였다. 따라서 본 연구에서는 유튜브도 다른 소셜 미디어와 같이 이용자가 상대적 박탈감을 느낀 다는 것을 확인 할 수 있었다.

Keywords

References

  1. M. H. Seo, "Influences of SNS Use on Life Satisfaction via Upward Social Comparison, Relative Deprivation and Underestimation of Economic Status," Korean Journal of Communication & Information, no. 83, pp. 72-95, Jun. 2017. https://doi.org/10.46407/kjci.2017.06.83.72
  2. H. S. Yang, "The Bright and Dark Sides of Reading Others via SNSs: Vicarious Pleasure, Inspiration, Feeling of Relative Deprivation, and Consequent Effects on Satisfaction with Life," Locality & Communication, vol. 23, no. 4, pp. 69-102, Nov. 2019. https://doi.org/10.47020/JLC.2019.11.23.4.69
  3. Youtube_Comment_Crawler [Internet]. Available : https://github.com/SOMJANG/Youtube_Comment_Crawler.
  4. K. J. Woo and S. H. Jeong, "Comparison of Korean Morphology Analyzers According to the Types of Sentence," Journal of Korean Institute of Information scientists and Engineers, PyeongChang Phoneix Park, pp. 1388-1390, Dec. 2019.
  5. From text to term frequency matrix [Internet]. Available : https://lovit.github.io/nlp/2018/03/26/from_text_to_matrix/.
  6. Naver sentiment movie corpus [Internet]. Available : https://github.com/e9t/nsmc.
  7. Sentimental Analysis with Deep Learning Models [Internet]. Available: https://wikidocs.net/44249.
  8. Why a Dentist's Daughter quit going to the School [Internet]. Available: https://www.youtube.com/watch?v=wIdId-0Hro0.
  9. Sentence Classification with Word2Vec [Internet]. Available : https://ratsgo.github.io/natural%20language%20processing/2017/03/08/word2vec/.
  10. H. S. Kang and J. H. Yang, "Analyzing Semantic Relations of Word Vectors trained by The Word2vec Model," Journal of Korean Institute of Information Scientists and Engineers, vol. 46, no. 10, pp. 1088-1093, Oct. 2019.