DOI QR코드

DOI QR Code

인플루언서 속성 분석 기반 추천 시스템

Influencer Attribute Analysis based Recommendation System

  • Park, JeongReun (Department of English Language and Literature, Ajou University) ;
  • Park, Jiwon (Department of English Language and Literature, Ajou University) ;
  • Kim, Minwoo (Department of Digital Media, Ajou University) ;
  • Oh, Hayoung (DASAN University College, Ajou University)
  • 투고 : 2019.07.16
  • 심사 : 2019.08.26
  • 발행 : 2019.11.30

초록

소셜 정보망의 발달로 마케팅의 방법도 다양하게 변화되고 있다. 기존의 유명인, 경제적 지원 기반의 성공적인 마케팅방법론과 달리, 최근 인플루언서 기반 유튜브 마케팅이 큰 대세를 이루고 있다. 본 논문 에서는 처음으로 유튜브 양적 정보 및 댓글분석 기반 다각도 질적 분석을 활용하여 54개 이상의 유튜브 채널에서 인플루언서 특징을 추출하고 대표적인 주제들을 모델링하여 개인 맞춤형 영상 만족도 극대화는 물론 기업체가 새로운 아이템을 마케팅 할 때 기존의 인플루언서 특징을 참고하여 새로운 아이템의 영상을 제작하고 배포함으로써 성공적인 홍보 효과를 누릴 수 있도록 보조 수단 제공을 목적으로 한다. 유튜브 채널 별 다양한 영상의 모든 댓글을 각 문서로 가정하고 TF-IDF 및 LDA알고리즘을 적용하여 성능 극대화 향상을 보였다.

With the development of social information networks, the marketing methods are also changing in various ways. Unlike successful marketing methods based on existing celebrities and financial support, Influencer-based marketing is a big trend and very famous. In this paper, we first extract influencer features from more than 54 YouTube channels using the multi-dimensional qualitative analysis based on the meta information and comment data analysis of YouTube, model representative themes to maximize a personalized video satisfaction. Plus, the purpose of this study is to provide supplementary means for the successful promotion and marketing by creating and distributing videos of new items by referring to the existing Influencer features. For that we assume all comments of various videos for each channel as each document, TF-IDF (Term Frequency and Inverse Document Frequency) and LDA (Latent Dirichlet Allocation) algorithms are applied to maximize performance of the proposed scheme. Based on the performance evaluation, we proved the proposed scheme is better than other schemes.

키워드

과제정보

This research was supported by the MIST (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW supervised by the IITP(Institute for Information & communications Technology Promotion)" (20150009080031001), Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Education(2017R1D1 A1B03035557) and Ajou University research fund.

참고문헌

  1. Y. I. Chang, and Y. S. Jung, "A Study on YouTube Product Review Channel Subscribers' Product Attitude Formation Process," The e-Business Studies, vol. 20, no. 2, pp. 77-97, Apr. 2019. https://doi.org/10.20462/TeBS.2019.4.20.2.77
  2. J. Davidson, B. Liebald, J. Liu, P. Nandy, and T. Van Vleet, "The YouTube Video Recommendation System" in Proceedings of the fourth ACM conference on Recommender systems, pp. 293-296, Apr. 2010.
  3. M. Kim, J. R. Park, J. W. Park, and H. Y. Oh, "Channel Attribute Analysis Scheme for Trustworthy Youtube Influencer Detection", in Proceeding of The 29th Joint Conference on Communications and Information on Big Data and Social Network, Apr. 2019.
  4. M. Kim, J. R. Park, J. W. Park, and H. Y. Oh, "Influencer Attribute Decision-Making based on Principal Component Analysis" in Proceeding of KIPS Conference on Web Science, pp. 672-674, May. 2019.
  5. J. W. Park, M. Kim, J. R. Park, and H. Y. Oh, "Stable Influencer Selection Criteria Scheme through Youtube Analysis of Hourly Comments" in Proceeding of Korea Institute of Next Generation Computing, Apr. 2019.
  6. P. Schultes, V. Dorner, and F. Lehner, "Leave a Comment! An In-Depth Analysis of User Comments on YouTube" in Proceeding Wirtschaftsinformatik Proceedings, pp. 659-673, Apr. 2013.
  7. J. R. Park, M. Kim, J. W. Park, and H. Y. Oh "A Study on Tools for Agent System Development" in Proceeding of KIPS Conference on information system, pp. 293-295, Apr. 2019.

피인용 문헌

  1. 인플루언서의 '뒷광고' 논란 전,후에 대한 댓글 비교 분석:LDA와 Word2vec을 중심으로 vol.20, pp.10, 2019, https://doi.org/10.5392/jkca.2020.20.10.119