DOI QR코드

DOI QR Code

토픽모델링을 활용한 인공지능 관련 이슈 분석

Analysis of Issues Related to Artificial Intelligence Based on Topic Modeling

  • 노설현 (안양대학교 ICT융합공학부 통계데이터과학전공)
  • Noh, Seol-Hyun (Department of Statistical Data Science, ICT Convergence Engineering, Anyang University)
  • 투고 : 2020.03.25
  • 심사 : 2020.05.20
  • 발행 : 2020.05.28

초록

본 연구는 국내의 인공지능과 관련된 기사들을 LDA 알고리즘에 기반한 토픽모델링 기법으로 분석하여 인공지능 관련 주요 이슈들을 도출하고 세부적으로 분석함으로써 인공지능 기술이 전(全) 산업 분야와 융합을 통해 창출할 수 있는 새로운 가치를 통찰하고, 인공지능 기술을 지식 경영에 적용할 수 있는 분야를 도출하는데 유용한 정보를 생산하고자 하였다. 본 연구에서는 '인공지능'을 검색어로 하여 추출된 11개의 중앙지와 8개의 경제지, 주요 방송사의 2016년부터 2019년까지 3,889건의 기사를 대상으로 오픈 소프트웨어인 R을 활용한 토픽모델링 기법을 사용하여 토픽 별 키워드들을 추출하였다. 각 토픽의 키워드 간 연관성을 나타내는 PMI(Pointwise Mutual Information) 측도를 높이도록 relevance 파라미터 λ를 최적화하여 토픽 별 키워드를 추출하였으며, 키워드들로부터 타당한 근거를 바탕으로 토픽명을 추론하였다. 추출된 토픽들은 인공지능 기술의 응용 분야와 사회, 경제, 산업, 문화 전반에서 일어나고 있는 변화 및 정부의 지원 정책과 비전을 폭 넓게 나타냈다.

The present study determined new value that can be created through the convergence between artificial intelligence technology (AIT) and all industries by deriving and thoroughly analyzing major issues related to artificial intelligence (AI). This study analyzes domestic articles related to AI using topic modeling method based on LDA algorithm. Keywords were extracted from 3,889 articles of eleven metropolitan newspapers, eight business newspapers and major broadcasting companies; articles were selected by searching for the keyword "artificial intelligence". Keywords were extracted by optimizing the relevance parameter λ to improve the measure of pointwise mutual information (PMI), which shows the association among the keywords of each topic, and topic names were inferred from keywords based on valid evidence. The extracted topics widely showed changes occurring throughout society, economy, industries, culture, and the support policy and vision of the government.

키워드

참고문헌

  1. KSBI. (2019). Global SME Policy Trend, 2(9).
  2. J. Park & M. Song. (2013). A study on the research trends in library & information science in Korea using topic modeling, Journal of the Korean society for information management, 30(1), 7-32. DOI : 10.3743/KOSIM.2013.30.1.007
  3. S. T. Flora. (2017). Blogger-link-topic model for blog mining, Pacific-Asia Conference on Knowledge Discovery and Data Mining, 28-39.
  4. J. H. Lau, N. Collier & T. Baldwin. (2012). On-line trend analysis with topic models: #twitter trends detection topic model online, Proceedings of COLING 2012, 1519-1534.
  5. D. H. Jeong & M. Song. (2014). Time gap analysis by the topic model-based temporal technique, Journal of Informetrics, 8(3), 776-790. DOI : 10.1016/j.joi.2014.07.005
  6. J. S. Park, S. G. Hong & J. W. Kim. (2017). A Study on Science Technology Trend and Prediction Using Topic Modeling, Journal of the Korea Industrial Information Systems Research, 22(4), 19-28. DOI : 10.9723/jksiis.2017.22.4.019
  7. M. S. Chung, S. H. Park, B. H. Chae & J. Y. Lee. (2017). Analysis of major research trends in artificial intelligence through analysis of thesis data, Journal of Digital Convergence, 15(5), 225-233. DOI : 10.14400/JDC.2017.15.5.225
  8. M. S. Chung, S. H. Jeong & J. Y. Lee. (2018). Analysis of major research trends in artificial intelligence based on domestic/international patent data, Journal of Digital Convergence, 16(6), 187-195. DOI : 10.14400/JDC.2018.16.6.187
  9. M. S. Chung & J. Y. Lee. (2018). Systemic Analysis of Research Activities and Trends Related to Artificial Intelligence(A.I.) Technology Based on Latent Dirichlet Allocation(LDA) Model, Journal of the Korea Industrial Information Systems Research, 23(3), 87-95. DOI : 10.9723/JKSIIS.2018.23.3.087
  10. S. Hwang & M. Kim. (2019). An analysis of artificial intelligence (A.I.)_related studies' trends in Korean focused on topic modeling and semantic network analysis, Journal of Digital Contents Society, 20(9), 1847-1855. https://doi.org/10.9728/dcs.2019.20.9.1847
  11. D. M. Blei, A. Y. Ng & M. I. Jordan. (2003). Latent Dirichlet allocation, Journal of Machine Learning Research, 3, 993-1022. DOI : 10.14400/JDC.2016.14.12.1
  12. C. Sievert & E. Shirley. (2014). LDAvis: A method for visualizing and interpreting topics, Proceedings of the Workshop on Interactive Learning, Visualization, and Interfaces, 63-70.
  13. D. Newman, S. Karimi & L. Cavedon. (2009). External evaluation of topic models, Proceedings of th 14th Australasian Document Computing Symposium, 11-18.
  14. S. Song. (2017). Historical development of industrial revolutions and the place of so called the fourth industrial revolution, Journal of Science and Technology Studies, 17(2), 5-40.
  15. P. R. Daugherty & H. J. Wilson (2018). Collaboration Intelligence, Human and AI Join Forces. Harvard Business Review Korea Magazine, July, 2018.
  16. A. Damasio. (1995). Descartes's Error: Emotion, Reason, and the Human Brain. Penguin Books.
  17. H. Yang et al. (2018). A Prospective Analysis of Artificial Intelligence(AI) Technology and Innovation Policies: Focused on Improving Korea's National AI R&D Policy. Policy Research 2018-13.
  18. EPRS. (2019). Economic impacts of artificial intelligence(AI). European Parliamentary Research Service PE637.967.
  19. COMPA. (2018). Autonomous Vehicles. S&T Market Report, 65.
  20. J. H. Lee. (2017). Impact of fintech spread on financial sector and audit implications, AIRI Research Report 2017-014.
  21. G. Y. Lee. (2016). Domestic and Overseas RoboAdvisor Trend and Status Analysis. e-Finance and Financial Security 2016-04.
  22. ETRI Standard Research Division. (2017). Blockchain, ETRI Standardization Trend 2017-2.
  23. PAX. (2019). State of AI: Artificial intelligence, the military and incresingly autonomous weapons.
  24. J. Y. Kim. (2019). Historical Patterns in the US-China AI Hegemonic Rivalry and the Latest Trend, SPRI SW Industry Trend.
  25. G. Lim. (2016). The digital management innovation of company in AI era, the direction to go forward, Seoul Economy Daily, https://www.sedaily.com/NewsVIew
  26. G. Lee. (2017). Artificial intelligence, a way to optimize management, Dong-A Business Review, https://dbr.donga.com/article/view/1101/article_no/8179