The Journal of Society for e-Business Studies (한국전자거래학회지)

Society for e-Business Studies (한국전자거래학회)
권호 표지
DOI QR코드

DOI QR Code

Mobile App Analytics using Media Repertoire Approach

미디어 레퍼토리를 이용한 스마트폰 애플리케이션 이용 패턴 유형 분석

  • Received : 2021.10.25
  • Accepted : 2021.11.27
  • Published : 2021.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Today smart phone is the most common media with a vehicle called 'application'. In order to understand how media users select applications and build their repertoire, this study conducted two-step approach using big data from smart phone log for 4 weeks in November 2019, and finally classified 8 media repertoire groups. Each of the eight media repertoire groups showed differences in time spent of mobile application category compared to other groups, and also showed differences between groups in demographic distribution. In addition to the academic contribution of identifying the mobile application repertoire with large scale behavioral data, this study also has significance in proposing a two-step approach that overcomes 'outlier issue' in behavioral data by extracting prototype vectors using SOM (Sefl-Organized Map) and applying it to k-means clustering for optimization of the classification. The study is also meaningful in that it categorizes customers using e-commerce services, identifies customer structure based on behavioral data, and provides practical guides to e-commerce communities that execute appropriate services or marketing decisions for each customer group.

현대인에게 가장 보편적이고 융합적인 미디어인 스마트 폰은 애플리케이션이라는 비히클을 갖는 뉴미디어이다. 이 연구는 미디어 사용자들은 어떻게 레퍼토리를 구성하여 미디어를 이용하고 있는지를 파악하고자 2019년 11월, 4주 동안의 개인별 모바일 이용행동 로그 데이터를 이용하여 모바일 애플리케이션 카테고리별 미디어 이용량을 중심으로 군집 분석을 실시하고, 최종적으로 8개의 모바일 미디어 레퍼토리 유형별 집단을 분류하였다. 8개의 각 미디어 레퍼토리 그룹은 애플리케이션 카테고리별 절대적 이용량과 타 그룹 대비 상대적 이용량에서 차이를 보였으며, 데모그라픽적 분포에서도 집단간 차이를 보였다. 이 연구는 모바일 미디어 레퍼토리를 규명해 냈다는 학문적 기여뿐만 아니라 기존의 k-means clustering에 의존적이었던 군집 분석을 SOM(Sefl-Organized Map)을 이용하여 프로토벡터를 추출하고 이 프로토벡터를 이용하여 k-means clustering을 실시하는 이단계 접근법(two-step approach)을 시도함으로써, 기존 k-means clustering이 갖고 있는 '이상치(outlier)'나 '결측치'에 민감했던 한계점을 극복하고 더 나은 성능의 분석 결과를 도출하고 있음을 보여준다는 점에서 방법론적으로도 의미를 갖는다. 또한 모바일 미디어 이용 행동의 유형 분류 연구는 전자거래 서비스를 이용하는 고객을 유형분류하고, 각 고객 유형에 맞는 고객 관리 서비스를 집행해야 하는 실무진이 고객 행동 로그 데이터를 기반으로 고객의 구조를 파악하고 각 고객 집단에 적합한 서비스 또는 마케팅 의사결정을 차별적으로 집행해야 하는 전자거래 커뮤니티에 실무적 가이드를 제공한다는 점에서도 의미를 갖고 있다.

Keywords

Acknowledgement

본 연구는 산업통상자원부 산업기술혁신사업의 지원을 받아 진행되었음(20009185).

References

  1. Boase, J., and Ling, R., "Measuring mobile phone use: Self-report versus log data," Journal of Computer-Mediated Communication, Vol. 18, No. 4, pp. 508-519, 2013. https://doi.org/10.1111/jcc4.12021
  2. Cheil Worldwide Inc, "Advertising Yearbook 2021," 2021.
  3. Choi, Y., Park, J., and Lee, H., "Factors affecting smart phone application's functional composition and repertoires," Social Science Review, Vol. 46, No. 1, pp. 163-198, 2015.
  4. Ferguson, D. A., and Perse, E. M., "The world wide web as a functional alternative to television," Journal of Broadcasting & Electronic Media, Vol. 44, No. 22, pp. 155-174, 2000. https://doi.org/10.1207/s15506878jobem4402_1
  5. Gan, G., and Ng, M. K. P., "K-means clustering with outlier removal," Pattern Recognition Letters, Vol. 90, pp. 8-14, 2017. https://doi.org/10.1016/j.patrec.2017.03.008
  6. Han, S. P., Park, S., and Oh, W, "Mobile app analytics: A multiple discrete-continuous choice framework," MIS Quarterly, Vol. 40, No. 4, pp. 989-1008, 2018.
  7. Ha, S., and Geum, Y., "Categorizing subcategories of mobile application services using network analysis: A case of healthcare applications," The Journal of Society for e-Business Studies, Vol. 25, No. 3, pp. 15-40, 2020. https://doi.org/10.7838/JSEBS.2020.25.3.015
  8. Ha, S., Oh, J., and Lee, B., "The analysis of advertisement effect in smart phone environment: The comparison of users with providers of commercial," The Journal of Society for e-Business Studies, Vol. 16, No. 4, pp. 221-239, 2011. https://doi.org/10.7838/JSEBS.2011.16.4.221
  9. Heeter, C., "Program selection with abundance of choice: A process model," Human Communication Research, Vol. 12, pp. 126-152, 1985. https://doi.org/10.1111/j.1468-2958.1985.tb00070.x
  10. Hu, M., and Lee, Y., "Reproducibility assessment of k-means clustering and applications," The Korean Journal of Applied Statistics, Vol. 17, No. 1, pp. 135-144, 2004. https://doi.org/10.5351/KJAS.2004.17.1.135
  11. Jung, J., Kim, Y., and Chan-Olmsted, S., "Measuring usage concentration of smartphone applications: Selective repertoire in a marketplace of choices," Mobile Media & Communication, Vol. 2, No. 3, pp. 352-368, 2014. https://doi.org/10.1177/2050157914542172
  12. Kang, N., Lee, J., and Lee, H., "Classifying media repertoires groups using k-mean cluster analysis method," Korean Journal of Broadcasting and Telecommunication Studies, Vol. 22 No. 2, pp. 7-46, 2008.
  13. Kim, E., Ha, Y., and Park, W., "A study on media repertoire and lifestyle," The Korean Journal of Advertising and Public Relations, Vol. 11, No. 1, pp. 61-95, 2009.
  14. Kim, S., and Kim, J., "A new cluster validity index based on connectivity in self-organizing map," The Korean Journal of Applied Statistics, Vol. 33, No. 5, pp. 591-601, 2020. https://doi.org/10.5351/KJAS.2020.33.5.591
  15. Kim, Y., Choi, Y., Kim, S., Park, K., and Park, J., "A study on method for user gender prediction using multi-modal smart device log data," The Journal of Society for e-Business Studies, Vol. 21, No. 1, pp. 147-163, 2016. https://doi.org/10.7838/JSEBS.2016.21.1.147
  16. Neuendorf, K. A., Atkin, D. J., and Jeffres, L. W., "Reconceptualizing channel repertoire in the urban cable environment," Journal of Broadcasting & Electronic Media, Vol. 45, No. 3, pp. 464-482, 2010. https://doi.org/10.1207/s15506878jobem4503_6
  17. Ormen, J., and Thorhauge, A. M., "Smartphone log data in a qualitative perspective," Mobile Media & Communication, Vol. 3, No. 3, pp. 335-350, 2015. https://doi.org/10.1177/2050157914565845
  18. Shim, M., "A study on media repertoire," Korean Journal of Broadcasting and Telecommunication Studies, Vol. 21, No. 2, pp. 351-390, 2007.
  19. Van Rees, K., and Van Eijck, K., "Media repertoires of selective audiences: The impact of status, gender, and age on media use," Poetics, Vol. 31, No. 5-6, pp. 465-490, 2003. https://doi.org/10.1016/j.poetic.2003.09.005
  20. Vesanto, J., and Alhoniemi, E., "Clustering of the self-organizing map," IEEE Transactions on Newral Networks and Learning Systems, Vol. 11, pp. 586-600, 2000. https://doi.org/10.1109/72.846731
  21. Webster, J. G., and Lin, S. F., "The internet audience: Web use as mass behavior," Journal of Broadcasting & Electronic Media, Vol. 46, No. 1, pp. 1-12, 2002. https://doi.org/10.1207/s15506878jobem4601_1