Journal of Information Technology Applications and Management

  • 제30권1호
  • /
  • Pages.53-70
  • /
  • 2023
  • /
  • 1598-6284(pISSN)
  • /
  • 2508-1209(eISSN)
한국데이터전략학회 (Korea Data Strategy Society)
권호 표지
DOI QR코드

DOI QR Code

소셜 네트워크 분석과 토픽 모델링을 활용한 설명 가능 인공지능 연구 동향 분석

XAI Research Trends Using Social Network Analysis and Topic Modeling

  • 투고 : 2023.02.02
  • 심사 : 2023.02.24
  • 발행 : 2023.02.28
⟨ 이전 논문 다음 논문 ⟩

초록

Artificial intelligence has become familiar with modern society, not the distant future. As artificial intelligence and machine learning developed more highly and became more complicated, it became difficult for people to grasp its structure and the basis for decision-making. It is because machine learning only shows results, not the whole processes. As artificial intelligence developed and became more common, people wanted the explanation which could provide them the trust on artificial intelligence. This study recognized the necessity and importance of explainable artificial intelligence, XAI, and examined the trends of XAI research by analyzing social networks and analyzing topics with IEEE published from 2004, when the concept of artificial intelligence was defined, to 2022. Through social network analysis, the overall pattern of nodes can be found in a large number of documents and the connection between keywords shows the meaning of the relationship structure, and topic modeling can identify more objective topics by extracting keywords from unstructured data and setting topics. Both analysis methods are suitable for trend analysis. As a result of the analysis, it was found that XAI's application is gradually expanding in various fields as well as machine learning and deep learning.

키워드

참고문헌

  1. Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K. R., and Samek, W., "On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation", PloS one, Vol. 10, No. 7, 2015, e0130140.
  2. Berry, M. and Linoff, "Data Mining Techniques: For Marketing, Sales, and Customer Support", Wiley,1997, ISBN: 0471179809, 9780471179801.
  3. Biecek, P., Chlebus, M., Gajda, J., Gosiewska, A., Kozak, A., Ogonowski, D. and Wojewnik, P., "Enabling Machine Learning Algorithms for Credit Scoring: Explainable Artificial Intelligence (XAI) methods for clear understanding complex predictive models", arXiv preprint arXiv:2104.06735, 2021.
  4. Blei, D. M., "Probabilistic topic models", Communications of the ACM, Vol. 55, No. 4, pp. 77-84, 2012. https://doi.org/10.1145/2133806.2133826
  5. Blei, D. M., Ng, A. Y., and Jordan, M. I., "Latent dirichlet allocation", The Journal of Machine Learning Research, Vol. 3, 2003, pp. 993-1022.
  6. Chen, B., "Deep Learning-Based Natural Language Processing Model for Explanable Personalization Recommendation Service", Kyunghee University, 2022.
  7. Chu, H., Shin, H., Choi, S., Yoo, Y., and Park, C., "Sensitivity Analysis Using Explainable AI for Building Energy Use", Journal of the Architectural Institute of Korea, Vol. 38, No. 11, 2022, pp. 279-287.
  8. Chun, Y., Kim, S., Lee, J., and Woo, J., "Study on credit rating model using explainable AI", Journal of the Korean Data And Information Science Society, Vol. 32, No. 2, 2021, pp. 283-295. https://doi.org/10.7465/jkdi.2021.32.2.283
  9. Deerwester, S., Dumais, S. T., Furnas, G. W., Landauer, T. K., and Harshman, R., "Indexing by latent semantic analysis", Journal of the American Society for Information Science, Vol. 41, No. 6, 1990, pp. 391-407. https://doi.org/10.1002/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9
  10. Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., and Pedreschi, D., "A survey of methods for explaining black box models", ACM Computing Surveys (CSUR), Vol. 51, No. 5, 2018, pp. 1-42. https://doi.org/10.1145/3236009
  11. Han, J. and Choi, J., "Explainable Artificial Intelligence", Journal of KSNVE, Vol. 27, No. 6, pp. 2017, 8-13.
  12. Han, S. and Kim, T., "News Big Data Analysis of 'Metaverse' Using Topic Modeling Analysis", Journal of Digital Contents Society, Vol. 22, No. 7, 2021, pp. 1091-1099. https://doi.org/10.9728/dcs.2021.22.7.1091
  13. Hansen, D., Shneiderman, B., and Smith, M. A., "Analyzing social media networks with NodeXL: Insights from a connected world", Morgan Kaufmann, 2010.
  14. Hofmann, T., "Probabilistic latent semantic indexing", In Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 1999, August, pp. 50-57.
  15. Hwang, H., "Sentiment Analysis based on Semi-Supervised Learning for using XAI", Seoul National University of Science and Technology, 2022.
  16. Hwang, S., "Knowledge graph-based UI for explainable recommendation", Yonsei University, 2021.
  17. Jaegal, D., "The Applicability of Social Network Analysis for Program Evaluation in Public Sector", Journal of Research Methodology, Vol.4, No.3, 2019, pp. 1-32. https://doi.org/10.21487/jrm.2019.11.4.3.1
  18. Jung, W., Yoon, J., and Kim, K., "Accounting Fraud Detection Using Forensic Techniques Based on Sentiment Analysis and Interpretable Machine Learning: Focused on Internal Control over Financial Reporting", Korean Accounting Review, Vol.46, No.6, 2021, pp. 181-218.
  19. Kang, K. and Park, S., "Keyword Analysis of KCI Journals on Business Administration using Web Crawling and Machine Learning", Korean Journal of Business Administration, Vol.32, No.4, 2019, pp. 597-615. https://doi.org/10.18032/kaaba.2019.32.4.597
  20. Kim, B., Jeong, M., Jeon, S., and Shin, D., "Global research trends on geospatial information by keyword network analysis", Journal of Korea Spatial Information Society, Vol.23, No.1, 2015, pp. 69-77 https://doi.org/10.12672/ksis.2015.23.1.069
  21. Kim, H. and Shin, S., "A Study on Explanable Artificial Intelligence (XAI)- based Machine Learning Feature Screening for Malicious Web Site Detection", Proceedings of Symposium of the Korean Institute of Communications and Information Sciences, 2020, pp. 411-412.
  22. Kim, M., Choi, J., and Kim, H., "The Framework of Research Network and Performance Evaluation on Personal Information Security: Social Network Analysis Perspective", Journal of Intelligence and Information System, Vol. 20, No. 1, 2014, pp. 177-193. https://doi.org/10.13088/jiis.2014.20.1.177
  23. Kim, M. and Hong, T., " Exploratory application of explainable artificial intelligence techniques to secure the reliability of deep learning-based personal credit evaluation model", Proceedings of the Korea Intelligent Information System Society Conference, 2022, pp. 194-194.
  24. Kim, S., Kim, D., and Kang, J., "A method suggesting the reason for the user recommendation: Design Sci Methodology methodology", Proceedings of Journal of Korea Service Management Society, 2022, pp. 130-130.
  25. Kim, S., Kim, W., Jang, Y., and Kim, H., "Development of Explainable AI-Based Learning Support System", The Journal of Korean Association of Computer Education, Vol. 24, No. 1, 2021, pp. 107-115.
  26. Kim, S. and Lee, G., "A Study on the Explainability and Hyperparameter Characteristics of Deep Neural Networks: A Case Study of SMEs Credit Scoring System", Journal of SME Finance, Vol.42, No.1, 2022, pp. 3-37. https://doi.org/10.33219/JSMEF.2022.42.1.001
  27. Kim, T., "COVID-19 News Analysis Using News Big Data: Focusing on Topic Modeling Analysis", The Journal of the Korea Contents Association, Vol. 20, No. 5, 2020, pp. 457-466.
  28. Lee, J., Park, J., Yoon, J., Lee, S., Yeom, S., Lee, Y., and Yoon, H., "Analyzing Precedents for Sports Match Fixing by Applying Topic Modeling", The Korean Journal of Measurement and Evaluation in Physical Education and Sports Science, Vol. 23, No. 2, 2021, pp. 51-65.
  29. Lee, S., Son, C., Shin, S., and Lee, K., "Airfoil Inverse Design using XAI(eXplainable Artificial Intelligence)", The Korean Society for Aeronautical and Space Sciences, 2021, pp. 50-51.
  30. Lundberg, S. and Lee, S., "A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems", 2017, pp. 4765-4774.
  31. Mohseni, S., Zarei, N., & Ragan, E. D. "A multidisciplinary survey and framework for design and evaluation of explainable AI systems", ACM Transactions on Interactive Intelligent Systems (TiiS), 11(3-4),2021, 1-45. https://doi.org/10.1145/3387166
  32. Moon, Y., "Analysis of Trends in Havruta Research based on Topic Modeling", The Journal of Learner-Centered Curriculum and Instruction, Vol. 20, No. 4, 2020, pp. 1149-1175. https://doi.org/10.22251/jlcci.2020.20.4.1149
  33. Oh, H., Son, A., and Lee, Z., "Occupational accident prediction modeling and analysis using SHAP", Journal of Digital Contents Society, Vol. 22, No. 7, 2021, pp. 1115-1123. https://doi.org/10.9728/dcs.2021.22.7.1115
  34. Park, J. and Kwak, K., "The Effect of Patent Citation Relationship on Business Performance : A Social Network Analysis Perspective", Journal of Intelligence and Information Systems, Vol. 19, No. 3, 2013, pp. 127-139. https://doi.org/10.13088/jiis.2013.19.3.127
  35. Park, S., Jeon, J., Kim, S., and Kim, S., "A Big-Data Analysis of Presidential Issue Ownership of two Prestigious Korean Newspapers: Focusing on LDA (latent Dirichlet allocation) Topic Modeling", The Journal of Political Science & Communication, Vol. 20, No. 3, 2017, pp. 25-55. https://doi.org/10.15617/psc.2017.10.31.3.25
  36. Ribeiro, M. T., Singh, S., and Guestrin, C., "Why should I trust you?" Explaining the predictions of any classifier", In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. pp. 1135-1144.
  37. Shin, K., Lee, Y., Bae, B., Lee, S., Hong, H., Choi, Y., and Lee, S., "Trustworthy AI Framework for Malware Response", Journal of the Korea Institute of Information Security & Cryptology, Vol. 32, No. 5, 2022, pp. 1019-1034.
  38. Shortliffe, Edward H., and Bruce, G., "A Model of inexact reasoning in medicine", Mathematical Biosciences, Vol.23, No.3-4, 1975, pp. 351-379. https://doi.org/10.1016/0025-5564(75)90047-4
  39. Son, J., Woo, S., Paek, H., Hwang, B., and Choi, S., "False positive reduction in anomaly detection using XAI", Proceedings of the Korean Information Science Society Conference, 2022, pp. 609-611.
  40. Van Lent, M., Fisher, W., and Mancuso, M. "An explainable artificial intelligence system for small-unit tactical behavior", IAAI'04: Proc. 16th Conf. on Innovative Applications of Artificial Intelligence (p./pp. 900-907), San Jose, CA, USA: AAAI Press, ISBN: 978-0-262-51183-4, 2004.