문화기술의 융합 (The Journal of the Convergence on Culture Technology)

  • 제9권4호
  • /
  • Pages.517-528
  • /
  • 2023
  • /
  • 2384-0358(pISSN)
  • /
  • 2384-0366(eISSN)
국제문화기술진흥원 (The International Promotion Agency of Culture Technology)
권호 표지
DOI QR코드

DOI QR Code

텍스트 마이닝을 활용한 커넥티드 카 고객 리뷰의 감성 분석: 국내-해외 브랜드간 UX 요인 비교를 중심으로

A Sentiment Analysis of Customer Reviews on the Connected Car using Text Mining: Focusing on the Comparison of UX Factors between Domestic-Overseas Brands

  • 신유정 (연세대학교 정보대학원 UX트랙) ;
  • 최준호 (연세대학교 정보대학원 UX트랙) ;
  • 김성우 (한림대학교 디지털인문예술전공)
  • 투고 : 2023.05.25
  • 심사 : 2023.07.02
  • 발행 : 2023.07.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

이 연구의 목적은 국내외 자동차 브랜드의 커넥티드 카 서비스의 사용자 감성 경험 요인들을 비교 분석하여 차이점을 도출하고 스마트 카 UX의 기획 방향성을 도출하는 것이다. 텍스트 마이닝 방법론을 활용하여, 국내외 브랜드 간 사용자 고객 리뷰의 경험 요인별 긍정-부정 감성 지수를 비교하였다. 현대차 그룹 브랜드 리뷰 12만 건과 해외 브랜드(테슬라, BMW, 벤츠) 리뷰 19만 건을 수집하여 전처리 과정을 수행한 후, 추출된 키워드를 연결 시스템, 정보, 서비스 차원에서 모두 11개의 경험 요인으로 분류하여 국내-해외 브랜드를 비교 분석하였다. 국내 커넥티드 카의 고객 리뷰 분석 결과, 가장 높은 감성 지수가 도출된 경험 요인은 '안전성'이었다. 해외 브랜드의 감성 지수 분석 결과, '오락성'이 가장 긍정적인 경험 요인으로 나타났다.

The purpose of this study is to analyze and compare UX factors of connectivity systems of domestic and overseas car brands. Using a text mining analysis, UX factors of domestic and overseas brands were compared through positive-negative sentiment index. After collecting 120,000 reviews on Hyundai Motor Group (Hyundai, Kia, Genesis) and 190,000 on Tesla, BMW, and Mercedes, pre-processing was performed. Keywords were classified into 11 UX factors in 3 dimensions of the system connection, information, and service. For domestic brands, sentiment index for 'safety' was the highest. For overseas brands, 'entertainment' was the most positive UX factor.

키워드

참고문헌

  1. Antons, D., Grunwald, E., Cichy, P., & Salge, T. O. (2020). The application of text mining methods in innovation research: Current state, evolution patterns, and development priorities. R&D Management, 50(3), 329-351. DOI: 10.1111/radm.12408
  2. Asghar, M. Z., Khan, A., Ahmad, S., & Kundi, F. M. (2014). A review of feature extraction in sentiment analysis. Journal of Basic and Applied Scientific Research, 4(3), 181-186.
  3. Auto Danawa. (2021, December). Automotive Sales Volume: Domestic, 2021. Auto Danawa Official Website. https://auto.danawa.com/auto/?Work=record&Tab=Grand&Nation=export&Month=2021-0100&MonthTo=2021-12-00/.
  4. Berezina, K., Bilgihan, A., Cobanoglu, C., & Okumus, F. (2016). Understanding satisfied and dissatisfied hotel customers: Text mining of online hotel reviews. Journal of Hospitality Marketing & Management, 25(1), 1-24. DOI: 10.1080/19368623.2015.983631
  5. Bertoncello, M. et al (2021). Unlocking the Full Life-cycle Value from Connected-Car Data. Mckinsey.
  6. Hyundai Motor Group (2022). Unlock the Software Age. https://www.youtube.com/watch?v=cZKcCG26VRI&t=1272s
  7. Choi, B, Lee, D. & Choi J.(2022). Semantic Network of User Experience in Automotive Connectivity Systems: Comparative Analysis of Korean and the US Automakers. The Journal of the Convergence on Culture Technology 8(1), 537-544. DOI:10.17703/JCCT.2022.8.1.537
  8. Viereckl, R., Assmann, J., & Raduge, C. (2014). In the Fast Lane: The Bright Future of Connected Cars. https://www.yumpu.com/en/document/view/52555888/in-the-fast-lane-the-bright-future-of-connected-cars
  9. Kim, J. W. (2012). Introduction to Human Computer Interaction, Ahn Graphics.
  10. Jung, J-H., Chung, H-I., & Lee, Z-K. (2021). An analysis of mobile food delivery app "Baemin" by using text mining and ARIMA Model. Journal of Digital Contents Society, 22(2), 291-299. DOI: 10.9728/dcs.2021.22.2.291
  11. Kaplan, A. M. & Haenlein, M. . (2010). Users of the World, Unite: The Challenges and Oppor tunities of Social Media. Business Horizons, 53(1), 59-68.DOI: https://doi.org/10.1016/j.bushor.2009.09.003/.
  12. Hong, L., & Davison, B. D. (2010, July). Empirical study of topic modeling in twitter. In Proceedings of the first workshop on Social Media Analytics (pp. 80-88). DOI: 10.1145/19648 58.1964870
  13. Blei, D. M., & Lafferty, J. D. (2009). Visualizing topics with multi-word expressions. arXiv preprint arXiv:0907.1013. DOI: 10.48550/arXiv.0907.1013
  14. Chang, J., Gerrish, S., Wang, C., Boyd-Graber, J., & Blei, D. (2009). Reading tea leaves: How humans interpret topic models. Advances In Neural Information Processing Systems, 22. DOI: 10.5555/2984093.2984126
  15. Sievert, C., & Shirley, K. (2014, June). LDAvis: A method for visualizing and interpreting topics. In Proceedings of the workshop on interactive language learning, visualization, and interfaces (pp. 63-70).DOI: 10.3115/v1/W14-3110
  16. Lee, S.-H., Kim, J., Yoon, S.-H., & Kim, H.-W. (2020). An analysis on key factors of mobile fitness application by using text mining techniques: User experience perspective. Journal of Information Technology Services, 19(3), 117-137. DOI: 10.9716/KITS.2020.19.3.117
  17. Berezina, K., Bilgihan, A., Cobanoglu, C., & Okumus, F. (2016).Understanding satisfied and dissatisfied hotel customers: text mining of online hotel reviews. Journal of Hospitality Marketing & Management, 25(1), 1-24.
  18. Lavin, M. (2019). Analyzing Dcuments with TF-IDF. DOI: 10.46430/phen0082
  19. Nanli, Z., Ping, Z., Weiguo, L. I., & Meng, C. (2012, November). Sentiment analysis: A literature review. In 2012 International Symposium on Management of Technology (ISMOT) (pp. 572-576). IEEE. DOI: 10.1109/ISMOT.2012.6679538
  20. Pang, B., & Lee, L. (2004). A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. arXiv preprint cs/0409058. DOI: 10.48550/arXiv.cs/0409058
  21. Park, J., Yang, D.-U., & Kim, H.-Y. (2021). Exploring user experience factors through generational online review analysis of AI speakers. Journal of the Korea Convergence Society, 12(7), 193-205. DOI: 10.15207/JKCS.2021.12.7.193
  22. Kim, H., Kim, J., & Choi. J. (2022) Effect of Anthropomorphic Chatbot's Self-disclosure and Emotional Expression on User Experience - Focused on Conversational Error in Financial Service.The Journal of the Convergence on Culture Technology, 8(4), 445-455.
  23. Shin, H & Choi, J. (2022). Analysis of User Reviews for Webtoon Applications Using Text Mining.The Journal of the Convergence on Culture Technology, 8(4), 457-468.