소셜네트워크 분석과 클러스터 분석 방법을 활용한 스타트업 회사의 트위터 팔로워 네트워크에 대한 탐색적 연구

Exploring Twitter Follower-Networks of Startup Companies Employing Social Network Analysis and Cluster Analysis

  • 투고 : 2019.08.20
  • 심사 : 2019.08.28
  • 발행 : 2019.08.31

초록

기업의 소셜미디어 활용이 빠른 속도로 증가함에 따라 성공적인 소셜미디어 활용전략의 중요성이 커지고 있다. 이러한 중요성은 새로이 시장에 진입하여 신속하게 시장에서의 인지도를 확대하고 미래고객을 확보해야 할 필요성이 큰 스타트업 회사에게 더욱 절실하다고 할 수 있다. 본 연구의 목적은 스타트업 회사의 소셜미디어 활용의 특징을 보여주는 지표를 탐색적으로 조사, 분석하는데 두고 있다. 주요 지표는 전반적인 소셜미디어 관련 활동을 보여주는 지표와 소셜미디어 서비스을 통해 형성된 소셜네트워크 구조의 특성과 관련 지표를 포함한다. 스타트업 회사의 이러한 지표를 좀 더 객관적으로 평가하기 위하여 잘 갖춰진 기존 회사의 지표와 비교, 분석 하였다. 본 연구를 위해 여러 소셜미디어 서비스 중 트위터를 선정하고, 트위터 REST API를 통해 측정지표와 관련된 데이터와 팔로워네트워크(follower-network)에 대한 데이터를 수집하였다. 주요 분석방법으로 각 회사의 소셜네트워크 구조의 특성을 분석하기 위해 소셜네트워크분석기법이 활용되었으며, 클러스터분석 기법을 이용하여 스타트업 회사와 기존 회사의 측정지표를 비교, 분석하였다. 분석결과에 따르면 대부분의 측정지표에서 스타트업 회사와 기존 회사 간에 유의미한 차이를 보여주고 있다. 특징적인 분석결과의 하나로 스타트업 회사들이 상대적으로 많은 수의 인플루언서 (influencer)를 팔로워네트워크에 가지고 있다는 점이다. 또한, 스타트업 회사를 포함하는 클러스터의 네트워크 모듈성(modularity)과 추이성(transitivity)이 기존 회사에 비해 상대적으로 높은 것으로 나타났다. 이러한 결과는 스타트업 회사의 소셜네트워크 안에 기존 회사에 비해 내부결속력이 높은 상대적으로 많은 수의 커뮤니티가 존재한다는 점을 시사한다고 할 수 있다. 스타트업 회사의 이러한 특징은 잠재고객 및 비즈니스 파트너와의 효과적인 정보교환을 촉진할 수 있으며, 따라서 향후 일반적인 스타트업 회사의 소셜미디어 노력은 어떻게 인플루언서를 확보할 것인지, 또한 어떻게 내부결속력이 높은 긴밀한 네트워크를 구축할 것인지에 초점을 두어야 할 필요성이 있음을 시사하고 있다.

The importance of business strategy for successful social media engagement has quickly increased as more businesses engage in social media. The importance is even greater for startup companies because startup companies are genuinely new to business, and they need to increase their presence in the market, and quickly access future customers. The objective of this paper lies in exploring key indicators of social media engagements by selected startup companies. The key indicators include two aspects of social media usages by the companies: i) overall social media activities, and ii) properties of network structure of the information flow platform provided by social media service. To better assess and evaluate the key indicators of social media usages by startup companies, the indicators will be compared with those of selected large established companies. Twitter is selected as a social media service for the analysis of this paper, and using Twitter REST API, data regarding the key indicators of overall Twitter activities and the Twitter follower-network of each company in the sample are collected. Then, the data are analyzed using social network analysis and hierarchical clustering analysis to examine the characteristics of the follower-network structures and to compare the characteristics between startup companies and established companies. The results show that most indicators are significantly different across startup companies and established companies. One key interesting finding is that the startup companies have proportionally more influencers in their follower-networks than the established companies have. Another interesting finding is that the follower-networks of startup companies in the sample have higher modularity and higher transitivity, suggesting that the startup companies tend to have a proportionally larger number of communities of users in their follower-networks, and the users in the networks are more tightly connected and cohesive internally. The key business implication for the future social media engagement efforts by startup companies in general is that startup companies may need to focus on getting more attention from influencers and promoting more cohesive communities in their follower-networks to appreciate the potential benefits of social media in the early stage of business of startup companies.

키워드

참고문헌

  1. Bansal, & Annika(2019). 10 Insightful Twitter Statistics for Small Business, SmallBusinessSense, Retrived from https://small-bizsense.com/10-insightful-twitter-statistics-for-small-business/
  2. Barnes, N. G., Allison, K., & Kyile, M. (2019). The 2018 Fortune 500 Target Millennials and Seek Uncensored Expression, Center for Marketing Research-UMass Dartmouth, Retrieved(2019/7/8) from https://www.umassd.edu/cmr/research/2018-fortune-500.html
  3. Bruns, A., & Stieglitz, S. (2013). Towards more systematic Twitter analysis: Metrics for tweeting activities. International Journal of Social Research Methodology, 16, 91-108. https://doi.org/10.1080/13645579.2012.756095
  4. Campbell, M. J., & Swinscow, T. D. V. (2009). Statistics at Square One, 11th ed. Wiley-Blackwell: BMJ Books
  5. Carley, K. (1991). A theory of group stability. American Sociological Review, 56, 331-354. https://doi.org/10.2307/2096108
  6. Clauset, A., Newman, M. E. J., & Moore, C. (2004), Finding community structure in very large networks, Phyisical Review, 70, 066111
  7. Csardi, G., & Nepusz, T. (2006). The igraph software package for complex network research, InterJourmal, Complex Systems 1695(5). http://igraph.org
  8. Ediger, D., Jiang, K., Riedy, J., Bader, D. A., & Corley, C. (2010). Massive social network analysis: Mining twitter for social good, In 2010 39th International Conference on Parallel Processing(583-593). New York, NY: IEEE.
  9. Freeman, L. C. (1979). Centrality in social networks conceptual clarification, Social networks 1(3), 215-239. https://doi.org/10.1016/0378-8733(78)90021-7
  10. Gentry, Jeff, G. (2015). twitteR: R Based Twitter Client. R package version 1.1.9. Retrieved(2019/3/15) from https://CRAN.R-project.org/package=twitteR
  11. Himelboim, I., & Han, J. Y. (2013). Cancer talk on Twitter: Patterns of information seeking in breast and prostate cancer networks. Journal of Health Communication, 19, 210-225. https://doi.org/10.1080/10810730.2013.811321
  12. Hansen, D. L., Shneiderman, B., & Smith, M. A. (2011). Analyzing social media networks with NodeXL: Insights from a connected world, Burlington, MA: Morgan Kaufmann.
  13. Kassambara, A., & Mundt, F. (2017). factoextra: Extract and Visualize the Results of Multivariate Data Analyses. R package version 1.0.5., Retrieved(2019/7/25) from https://CRAN.R-project.org/package=factoextra
  14. Kearney, M. W. (2019). rtweet: Collecting Twitter Data. R package version 0.6.9, Retrieved (2019/3/15) from https://cran.r-project.org/package=rtweet
  15. Ketchen, Jr, D. J., & Shook, C. L. (1996). The application of cluster analysis in Strategic Management Research: An analysis and critique, Strategic Management Journal, 17(6), 441-458. https://doi.org/10.1002/(SICI)1097-0266(199606)17:6<441::AID-SMJ819>3.0.CO;2-G
  16. Kumar, R., Novak, J., & Tomkins, A. (2006). Structure and evolution of online social networks. Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Philadelphia, PA.
  17. Lerman, K., & Ghosh, R. (2010). Information contagion: An empirical study of the spread of news on Digg and Twitter social networks. ICWSM, 10, 90-97.
  18. Maechler, M., Rousseeuw, P., Struyf, A., Hubert, M., & Hornik, K. (2019). cluster: Cluster Analysis Basics and Extensions, R package version 2.1.0.
  19. Newman, M. E., & Girvan, M. (2004). Finding and evaluating community structure in networks. Physical Review E, 69(2), 026113. https://doi.org/10.1103/PhysRevE.69.026113
  20. Ranker(2019). Fortune 100 Companies on Twitter: Corporate Twitter Accounts, Retrieved (2019/6/15) from https://www.ranker.com/list/fortune-100-companies-on-twitter-corporate-twitter-accounts/business-and-company-info
  21. Rousseeuw, P. J. (1987). Silhouettes: A graphical aid to the interpretation and validation of cluster analysis, J. Comput. Appl. Math., 20, 53-65. https://doi.org/10.1016/0377-0427(87)90125-7
  22. Sajid, Arsalan(2019). 60 Best Startups You Need to Watch Out for in 2019, Retrieved (2019/6/10) from https://www.cloudways.com/blog/best-startups-watch-out/
  23. Ward, J. H., Jr. (1963). Hierarchical Grouping to Optimize an Objective Function, Journal of the American Statistical Association, 58, 236-244. https://doi.org/10.1080/01621459.1963.10500845
  24. Wasserman, S., & Faust, K. (1994). Social network analysis: Methods and applications, New York, NY: Cambridge University Press.
  25. Yamane, T. (1967). Statistics: An Introductory Analysis, 2nd Edition, New York: Harper and Row.