KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis of Social Trends for Electric Scooters Using Dynamic Topic Modeling and Sentiment Analysis

동적 토픽 모델링과 감성 분석을 활용한 전동킥보드에 대한 사회적 동향 분석

  • 김경옥 (서울과학기술대학교 산업공학과) ;
  • 신예랑 (서울과학기술대학교 데이터사이언스학과)
  • Received : 2022.02.15
  • Accepted : 2022.05.10
  • Published : 2023.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

An electric scooter(e-scooter), one popularized micro-mobility vehicle has shown rapidly increasing use in many cities. In South Korea, the use of e-scooters has greatly increased, as some companies have launched e-scooter sharing services in a few large cities, starting with Seoul in 2018. However, the use of e-scooters is still controversial because of issues such as parking and safety. Since the perception toward the means of transportation affects the mode choice, it is necessary to track the trends for electric scooters to make the use of e-scooters more active. Hence, this study aimed to analyze the trends related to e-scooters. For this purpose, we analyzed news articles related to e-scooters published from 2014 to 2020 using dynamic topic modeling to extract issues and sentiment analysis to investigate how the degree of positive and negative opinions in news articles had changed. As a result of topic modeling, it was possible to extract three different topics related to micro-mobility technologies, shared e-scooter services, and regulations for micro-mobility, and the proportion of the topic for regulations for micro-mobility increased as shared e-scooter services increased in recent years. In addition, the top positive words included quick, enjoyable, and easy, whereas the top negative words included threat, complaint, and ilegal, which implies that people satisfied with the convenience of e-scooter or e-scooter sharing services, but safety and parking issues should be addressed for micro-mobility services to become more active. In conclusion, this study was able to understand how issues and social trends related to e-scooters have changed, and to determine the issues that need to be addressed. Moreover, it is expected that the research framework using dynamic topic modeling and sentiment analysis will be helpful in determining social trends on various areas.

마이크로 모빌리티 중 하나인 전동킥보드의 이용은 세계적으로 급격히 성장하고 있는 추세이다. 국내에서는 2018년 서울에서 서비스를 시작한 킥고잉을 비롯하여 서울을 포함한 일부 대도시에서 공유킥보드 서비스를 제공하는 업체가 생기면서 전동킥보드의 이용이 크게 증가했다. 하지만, 전동킥보드의 이용은 여전히 주차, 안전에 대한 문제로 인해 논란의 대상이 되고 있다. 이동수단에 대한 인식은 사용자들이 어떤 이동수단을 선택할지에도 영향을 끼치므로 전동킥보드 이용 및 공유킥보드 서비스 활성화를 위해서는 관련 이슈와 그에 대한 대중의 인식을 파악할 필요가 있다. 이에 본 연구에서는 전동킥보드 관련 이슈에 대한 사회적 동향을 파악하는 것을 목표로 시간에 따른 이슈의 변동성을 고려해 동적 토픽 모델링과 감성 분석을 활용하여 2014년에서 2020년까지의 전동킥보드 관련 뉴스 기사를 분석하였다. 토픽 모델링을 통해 마이크로 모빌리티 기술, 공유킥보드 서비스, 킥보드 관련 규제 관련 토픽을 도출하였으며, 공유킥보드 서비스 증가와 함께 안전에 대한 이슈가 크게 불거지면서 킥보드에 대한 규제 관련 토픽의 비중이 최근 들어 크게 증가함을 확인했다. 그뿐만 아니라 감성 분석을 통해 킥보드 관련 뉴스에 주로 등장하는 긍정어는 신속, 즐기다, 손쉽다, 편리 등이 있고 부정어는 위협, 불법, 침해 등으로 나타나 킥보드나 공유킥보드 서비스의 편의성에는 만족하지만, 마이크로 모빌리티 서비스에서 안전, 주차 등의 문제는 여전히 해결해야하는 이슈임을 알 수 있었다. 결론적으로, 본 연구를 통해 전동킥보드에 대한 이슈와 그에 대한 관심과 사회적 감성의 변화를 확인하고 어떤 이슈에 대한 대응이 필요한지 파악할 수 있었다. 이 연구의 분석의 틀은 향후 다양한 사회 현안에 대한 사회적 동향을 파악하고 그에 대한 대응 방안을 마련하는데 활용할 수 있을 것으로 기대된다.

Keywords

Acknowledgement

이 성과는 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(No. 2020R1F1A1054496).

References

  1. S. Sultana, D. Salon, and M. Kuby, "Transportation sustainability in the urban context: A comprehensive review," Urban Geography, Vol.40, No.3, pp.279-308, 2019. https://doi.org/10.1080/02723638.2017.1395635
  2. S. Jappinen, T. Toivonen, and M. Salonen, "Modelling the potential effect of shared bicycles on public transport travel times in Greater Helsinki: An open data approach," Applied Geography, Vol.43, pp.13-24, 2013. https://doi.org/10.1016/j.apgeog.2013.05.010
  3. B. Madapur, S. Madangopal, and M. N. Chandrashekar, "Micro-Mobility Infrastructure for Redefining Urban Mobility," European Journal of Engineering Science and Technology, Vol.3, No.1, pp.71-85, 2020. https://doi.org/10.33422/ejest.v3i1.163
  4. G. McKenzie, "Urban mobility in the sharing economy: A spatiotemporal comparison of shared mobility services," Computers, Environment and Urban Systems, Vol.79, pp.101418, 2020.
  5. J. K. Mathew, M. Liu, and D. M. Bullock, "Impact of Weather on Shared Electric Scooter Utilization," Proceedings of the 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pp.4512-4516, 2019.
  6. NACTO, "Shared Micromobility in the U.S.: 2019," 2020.
  7. Gyeonggi Research Institute. "Smart mobility services: Issue and policy implications," 2020.
  8. M. J, Park, "A controversy over whether the Scooter-sharing Service is an Innovation or not: 2,000 Complaints Have Been Filed due to Abandoned Scooters," Korea Joong-Ang Daily Economy, p.1, 2020.
  9. H. H. Jo, H. S. Noh, H. C. Yoo, J. Kang, J. Jung, H. S. Kim, "A study on the use behavior and safety of electric scooters - Focused on the survey of e-scooter owners," Geographical Journal of Korea, Vol.55, No.1, pp.43-55, 2021. https://doi.org/10.22905/kaopqj.2021.55.1.4
  10. S. Y. Ko, "A study on the change of movement environment according to increase of personal mobility focusing on the road environment of highway safety and drivers using secure walkers," Korea Institute of Design Research Society, Vol.2, No.3, pp.9-17, 2017.
  11. T. Eccarius and C. C. Lu, "Adoption intentions for micro-mobility-Insights from electric scooter sharing in Taiwan," Transportation Research Part D: Transport And Environment, Vol.84, pp.102327, 2020.
  12. H. Fitt and A. Curl, "The early days of shared micromobility: A social practices approach," Journal of Transport Geography, Vol.86, pp.102779, 2020.
  13. J. J. Aman, J. Smith-Colin, and W. Zhang, "Listen to E-scooter riders: Mining rider satisfaction factors from app store reviews," Transportation Research Part D: Transport and Environment, Vol.95, pp.102856, 2021.
  14. Y. Feng, et al., "Micromobility in smart cities: A closer look at shared dockless E-Scooters via big social data," ICC 2021-IEEE International Conference on Communications, IEEE, 2021.
  15. H. S. Lee, K. H. Baek, J. H. Jeong, and J. H. Kim, "User's behaviors of smart personal mobility sharing services: Emperical evidence from electric scooter sharing service," Proceedings of the KOR-KST Conference, pp.462-463, 2019.
  16. S. J. Kim, S. Choo, and S. H. Kim, "A study on the usage pattern of E-Scooter sharing service," Proceedings of the KOR-KST Conference, pp.344-345, 2020.
  17. KISO Planning Team, "Domestic trends and expected effects of 'Shared Electric Kickboards'," 2019. [Internet], https://journal.kiso.or.kr/?p=9850.
  18. D. M. Blei, A. Y. Ng, and M. I. Jordan, "Latent dirichlet allocation," Journal of Machine Learning Research, Vol.3, pp.993-1022, 2003.
  19. S. A. Jin, G. E. Heo, Y. K. Jeong, and M. Song, "Topic-network based topic shift detection on twitter," Journal of the Korean Society for information Management, Vol.30, No.1, pp.285-302, 2013. https://doi.org/10.3743/KOSIM.2013.30.1.285
  20. D. M. Blei and J. D. Lafferty, "Dynamic topic models," Proceedings of the 23rd International Conference on Machine Learning, 2006.
  21. A. Daud, "Using time topic modeling for semantics-based dynamic research interest finding," Knowledge-Based Systems, Vol.26, pp.154-163, 2012. https://doi.org/10.1016/j.knosys.2011.07.015
  22. H. Zhang, G. Kim, and E. P. Xing, "Dynamic topic modeling for monitoring market competition from online text and image data," Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2015.
  23. T. U. Haque, N. N. Saber, and F. M. Shah, "Sentiment analysis on large scale Amazon product reviews," 2018 IEEE International Conference on Innovative Research and Development (ICIRD), IEEE, 2018.
  24. L. Jiang and Y. Suzuki, "Detecting hate speech from tweets for sentiment analysis," 2019 6th International Conference on Systems and Informatics (ICSAI). IEEE, 2019.
  25. D. Tumitan and K. Becker, "Sentiment-based features for predicting election polls: A case study on the brazilian scenario," 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT). 2. IEEE, 2014.
  26. M. Taboada, J. Brooke, M. Tofiloski, K. Voll, and M. Stede, "Lexicon-based methods for sentiment analysis," Computational linguistics, Vol.37, No.2, pp.267-307, 2011. https://doi.org/10.1162/COLI_a_00049
  27. M. Z. Asghar, A. Khan, S. Ahmad, M. Qasim, and I. A. Khan, "Lexicon-enhanced sentiment analysis framework using rule-based classification scheme," PloS one, Vol.12, No.2, pp.e0171649, 2007.
  28. K. Erk, "Vector space models of word meaning and phrase meaning: A survey," Language and Linguistics Compass, Vol.6, No.10, pp.635-653, 2012. https://doi.org/10.1002/lnco.362
  29. Q. Le and T. Mikolov, "Distributed representations of sentences and documents," Proceedings of the 31st International Conference on Machine Learning, Vol.32, pp. 1188-1196, 2014.
  30. G. Rao, W. Huang, Z. Feng, and Q. Cong, "LSTM with sentence representations for document-level sentiment classification," Neurocomputing, Vol.308, pp.49-57, 2018. https://doi.org/10.1016/j.neucom.2018.04.045
  31. Z. Gao, A. Feng, X. Song, and X. Wu, "Target-dependent sentiment classification with BERT," IEEE Access, Vol.7, pp.154290-154299, 2019. https://doi.org/10.1109/access.2019.2946594
  32. M. Munikar, S. Shakya, and A. Shrestha, "Fine-grained Sentiment Classification using BERT," Proceedings of the 2019 Artificial Intelligence for Transforming Business and Society (AITB), Vol.1, pp.1-5, 2019.
  33. S. Lee, H. Jang, Y. Baik, S. Park, and H. Shin, "Kr-bert: A small-scale korean-specific language model," arXiv Prepr. arXiv2008.03979, 2020.
  34. D. Hyun, J. Cho, and H. Yu, "Building large-scale english and korean datasets for aspect-level sentiment analysis in automotive domain," Proceedings of the 28th International Conference on Computational Linguistics, 2020.
  35. W. Medhat, A. Hassan, and H. Korashy, "Sentiment analysis algorithms and applications: A survey," Ain Shams Engineering Journal, Vol.5, No.4, pp.1093-1113, 2014. https://doi.org/10.1016/j.asej.2014.04.011
  36. T. Ito, K. Tsubouchi, H. Sakaji, T. Yamashita, and K. Izumi, "Contextual sentiment neural network for document sentiment analysis," Data Science and Engineering, Vol.5, No.2, pp.180-192, 2020. https://doi.org/10.1007/s41019-020-00122-4
  37. M. E. Basiri, S. Nemati, M. Abdar, E. Cambria, and U. R. Acharya, "ABCDM: An attention-based bidirectional CNNRNN deep model for sentiment analysis," Future Generation Computer Systems, Vol.115, pp.279-294, 2021. https://doi.org/10.1016/j.future.2020.08.005
  38. H. Jang, M. Kim, and H. Shin, "KOSAC: A full-fledged Korean sentiment analysis corpus," Proceedings of the 27th Pacific Asia Conference on Language, Information, and Computation, pp.366-373, 2013.
  39. H. P. Shin, M. H. Kim, and S. Z. Park, "Modality-based sentiment analysis through the utilization of the Korean sentiment analysis corpus," Journal of the Linguistic Society of Korea, Vol.74, pp.93-114, 2016. https://doi.org/10.17290/jlsk.2016..74.93
  40. S. B. Kim, S. J. Kwon, and J. T. Kim, "Building sentiment dictionary and polarity classification of blog review By using elastic net," Proceedings of Korean Institute of Information Scientists and Engineers, pp.639-641, 2015.