지능정보연구 (Journal of Intelligence and Information Systems)

  • 제29권3호
  • /
  • Pages.185-209
  • /
  • 2023
  • /
  • 2288-4866(pISSN)
  • /
  • 2288-4882(eISSN)
한국지능정보시스템학회 (Korea Intelligent Information System Society)
권호 표지
DOI QR코드

DOI QR Code

BERTopic을 활용한 인간-로봇 상호작용 동향 연구

A Study on Human-Robot Interaction Trends Using BERTopic

  • 김정훈 (국민대학교 비즈니스IT전문대학원 4단계 BK21 교육연구팀) ;
  • 곽기영 (국민대학교 경영대학/비즈니스 IT전문대학원)
  • Jeonghun Kim (Graduate School of Business IT, Kookmin University) ;
  • Kee-Young Kwahk (College of Business Administration / Graduate School of Business IT, Kookmin University)
  • 투고 : 2023.02.10
  • 심사 : 2023.08.31
  • 발행 : 2023.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

4차 산업혁명의 도래와 함께 다양한 기술이 주목을 받고 있다. 4차 산업혁명과 관련된 기술로는 IoT(Internet of Things), 빅데이터, 인공지능, VR(Virtual Reality), 3D 프린터, 로봇공학 등이 있으며 이러한 기술은 종종 융합된다. 특히 로봇 분야는 빅데이터, 인공지능, VR, 디지털 트윈과 같은 기술과 결합할 것으로 기대된다. 이에 따라 로봇을 활용한 연구가 다수 진행되고 있으며 유통, 공항, 호텔, 레스토랑, 교통 분야 등에 적용되고 있다. 이러한 상황에서 인간-로봇 상호작용에 대한 연구가 주목을 받고 있지만 아직 만족할 만한 수준에는 이르지 못하고 있다. 하지만 완벽한 의사소통이 가능한 로봇에 대한 연구가 꾸준히 이루어지고 있고 이는 인간의 감정노동을 대신할 수 있을 것으로 기대된다. 따라서 현재의 인간-로봇 상호작용 기술을 비즈니스에 적용할 수 있는지에 대한 논의가 필요하다. 이를 위해 본 연구는 첫째, 인간로봇 상호작용 기술의 동향을 살펴본다. 둘째, LDA(Latent Dirichlet Allocation) 토픽모델링과 BERTopic 토픽모델링 방법을 비교한다. 연구 결과, 1992년~2002년 간의 연구에서는 인간-로봇 상호작용에 대한 개념과 기초적인 상호작용에 대해 논의되고 있었다. 2003년~2012년에는 사회적 표현에 대한 연구가 많이 진행되었으며 얼굴검출, 인식 등과 같이 판단과 관련된 연구도 수행되었다. 2013년~2022년에는 노인 간호, 교육, 자폐 치료와 같은 서비스 토픽들이 등장하였으며, 사회적 표현에 대한 연구가 지속되었다. 그러나 아직까지 비즈니스에 적용할 수 있는 수준에는 이르지 못한 것으로 보인다. 그리고 LDA토픽모델링과 BERTopic 토픽모델링 방법을 비교한 결과 LDA에 비해 BERTopic이 더 우수한 방법임을 확인하였다.

With the advent of the 4th industrial revolution, various technologies have received much attention. Technologies related to the 4th industry include the Internet of Things (IoT), big data, artificial intelligence, virtual reality (VR), 3D printers, and robotics, and these technologies are often converged. In particular, the robotics field is combined with technologies such as big data, artificial intelligence, VR, and digital twins. Accordingly, much research using robotics is being conducted, which is applied to distribution, airports, hotels, restaurants, and transportation fields. In the given situation, research on human-robot interaction is attracting attention, but it has not yet reached the level of user satisfaction. However, research on robots capable of perfect communication is steadily being conducted, and it is expected that it will be able to replace human emotional labor. Therefore, it is necessary to discuss whether the current human-robot interaction technology can be applied to business. To this end, this study first examines the trend of human-robot interaction technology. Second, we compare LDA (Latent Dirichlet Allocation) topic modeling and BERTopic topic modeling methods. As a result, we found that the concept of human-robot interaction and basic interaction was discussed in the studies from 1992 to 2002. From 2003 to 2012, many studies on social expression were conducted, and studies related to judgment such as face detection and recognition were conducted. In the studies from 2013 to 2022, service topics such as elderly nursing, education, and autism treatment appeared, and research on social expression continued. However, it seems that it has not yet reached the level that can be applied to business. As a result of comparing LDA (Latent Dirichlet Allocation) topic modeling and the BERTopic topic modeling method, it was confirmed that BERTopic is a superior method to LDA.

키워드

참고문헌

  1. 강은경, 정연식, 양선욱, 권지윤, & 양성병. (2022). MIS Quarterly 연구동향 탐색: 토픽모델링 및 키워드 네트워크 분석 활용. 지능정보연구, 28(2), 207-235.
  2. 김민구, 김용우, 정태현, & 김영민. (2022). Organic Light-Emitting Diodes 디스플레이 기술의 특허 동향과 기술적 가치에 관한 탐색적 연구. 지능정보연구, 28(4), 135-155.
  3. 문길성. (2021). 단문의 주제 분석을 위한 LDA 와 BTM 토픽모형 평가. Journal of The Korean Data Analysis Society, 23(3), 1313-1326. 
  4. Alnusyan, R., Almotairi, R., Almufadhi, S., Shargabi, A. A., & Alshobaili, J. (2020, September). A semi-supervised approach for user reviews topic modeling and classification. In 2020 International Conference on Computing and Information Technology (ICCIT-1441) (pp. 1-5). IEEE.
  5. Angelov, D. (2020). Top2vec: Distributed representations of topics. arXiv preprint arXiv:2008.09470.
  6. Ao, Z., Horvath, G., Sheng, C., Song, Y., & Sun, Y. (2023). Skill requirements in job advertisements: A comparison of skill-categorization methods based on wage regressions. Information Processing & Management, 60(2), 103185.
  7. Arnold, T., & Scheutz, M. (2017). The tactile ethics of soft robotics: Designing wisely for human-robot interaction. Soft robotics, 4(2), 81-87.
  8. Bergamaschi, S., Po, L., & Sorrentino, S. (2014, April). Comparing topic models for a movie recommendation system. In International Conference on Web Information Systems and Technologies (Vol. 2, pp. 172-183). SciTePress.
  9. Bethel, C. L., & Murphy, R. R. (2007). Survey of non-facial/non-verbal affective expressions for appearance-constrained robots. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 38(1), 83-92.
  10. Blei, D. M. (2012). Probabilistic topic models. Communications of the ACM, 55(4), 77-84. https://doi.org/10.1145/2133806.2133826
  11. Broadbent, E. (2017). Interactions with robots: The truths we reveal about ourselves. Annual review of psychology, 68, 627-652. https://doi.org/10.1146/annurev-psych-010416-043958
  12. Burke, J. L., Murphy, R. R., Rogers, E., Lumelsky, V. J., & Scholtz, J. (2004). Final report for the DARPA/NSF interdisciplinary study on human-robot interaction. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 34(2), 103-112.
  13. Carros, F., Meurer, J., Loffler, D., Unbehaun, D., Matthies, S., Koch, I., ... & Wulf, V. (2020, April). Exploring human-robot interaction with the elderly: results from a ten-week case study in a care home. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (pp. 1-12).
  14. Celuch, K. (2020). Customers' experience of purchasing event tickets: mining online reviews based on topic modeling and sentiment analysis. International Journal of Event and Festival Management, 12(1), 36-50. https://doi.org/10.1108/IJEFM-06-2020-0034
  15. Chan, J., & Nejat, G. (2012). Social intelligence for a robot engaging people in cognitive training activities. International Journal of Advanced Robotic Systems, 9(4), 113.
  16. Chandrasekaran, B., & Conrad, J. M. (2015, April). Human-robot collaboration: A survey. In SoutheastCon 2015 (pp. 1-8). IEEE.
  17. Chuah, S. H. W., & Yu, J. (2021). The future of service: The power of emotion in human-robot interaction. Journal of Retailing and Consumer Services, 61, 102551.
  18. Chuah, S. H. W., & Yu, J. (2021). The future of service: The power of emotion in human-robot interaction. Journal of Retailing and Consumer Services, 61, 102551.
  19. Churchill, R., & Singh, L. (2022). The evolution of topic modeling. ACM Computing Surveys, 54(10s), 1-35.
  20. de Visser, E., & Parasuraman, R. (2011). Adaptive aiding of human-robot teaming: Effects of imperfect automation on performance, trust, and workload. Journal of Cognitive Engineering and Decision Making, 5(2), 209-231.
  21. Egger, R., & Yu, J. (2022). A topic modeling comparison between lda, nmf, top2vec, and bertopic to demystify twitter posts. Frontiers in sociology, 7, 886498.
  22. Fang, H. C., Ong, S. K., & Nee, A. Y. C. (2014). A novel augmented reality-based interface for robot path planning. International Journal on Interactive Design and Manufacturing (IJIDeM), 8, 33-42.
  23. Feldman, R., & Dagan, I. (1995, August). Knowledge Discovery in Textual Databases (KDT). In KDD (Vol. 95, pp. 112-117).
  24. Gallagher, R. J., Reing, K., Kale, D., & Ver Steeg, G. (2017). Anchored correlation explanation: Topic modeling with minimal domain knowledge. Transactions of the Association for Computational Linguistics, 5, 529-542.
  25. Goldin-Meadow, S. (1999). The role of gesture in communication and thinking. Trends in cognitive sciences, 3(11), 419-429. https://doi.org/10.1016/S1364-6613(99)01397-2
  26. Goodrich, M. A., & Schultz, A. C. (2008). Human-robot interaction: a survey. Foundations and Trends® in Human-Computer Interaction, 1(3), 203-275.
  27. Griffiths, T. L., Steyvers, M., & Tenenbaum, J. B. (2007). Topics in semantic representation. Psychological review, 114(2), 211.
  28. Grootendorst, M. (2022). BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794.
  29. Hall, E. T. (1966). The hidden dimension (Vol. 609). Anchor.
  30. Hancock, P. A., Billings, D. R., Schaefer, K. E., Chen, J. Y., De Visser, E. J., & Parasuraman, R. (2011). A meta-analysis of factors affecting trust in human-robot interaction. Human factors, 53(5), 517-527.
  31. Henschel, A., Hortensius, R., & Cross, E. S. (2020). Social cognition in the age of human-robot interaction. Trends in Neurosciences, 43(6), 373-384.
  32. Hentout, A., Aouache, M., Maoudj, A., & Akli, I. (2019). Human-robot interaction in industrial collaborative robotics: a literature review of the decade 2008-2017. Advanced Robotics, 33(15-16), 764-799.
  33. Hofmann, T. (1999, August). Probabilistic latent semantic indexing. In Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval (pp. 50-57).
  34. Hofmann, T. (1999, August). Probabilistic latent semantic indexing. In Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval (pp. 50-57).
  35. Jelodar, H., Wang, Y., Yuan, C., Feng, X., Jiang, X., Li, Y., & Zhao, L. (2019). Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey. Multimedia Tools and Applications, 78, 15169-15211.
  36. Joe, W. Y., & Song, S. Y. (2019). Applying human-robot interaction technology in retail industries. International Journal of Mechanical Engineering and Robotics Research, 8(6), 839-844.
  37. Kim, Y., & Mutlu, B. (2014). How social distance shapes human-robot interaction. International Journal of Human-Computer Studies, 72(12), 783-795.
  38. Kukushkin, K., Ryabov, Y., & Borovkov, A. (2022). Digital twins: A systematic literature review based on data analysis and topic modeling. Data, 7(12), 173.
  39. Lee, J., Park, H. A., Park, S. K., & Song, T. M. (2020). Using social media data to understand consumers' information needs and emotions regarding cancer: ontology-based data analysis study. Journal of Medical Internet Research, 22(12), e18767.
  40. Li, J., Louie, W. Y. G., Mohamed, S., Despond, F., & Nejat, G. (2016, December). A user-study with tangy the bingo facilitating robot and long-term care residents. In 2016 IEEE international symposium on robotics and intelligent sensors (IRIS) (pp. 109-115). IEEE.
  41. Lu, L., Cai, R., & Gursoy, D. (2019). Developing and validating a service robot integration willingness scale. International Journal of Hospitality Management, 80, 36-51.
  42. Malik, A. A., & Brem, A. (2021). Digital twins for collaborative robots: A case study in human-robot interaction. Robotics and Computer-Integrated Manufacturing, 68, 102092.
  43. Nass, C., & Moon, Y. (2000). Machines and mindlessness: Social responses to computers. Journal of social issues, 56(1), 81-103.
  44. Nehaniv, C. L., Dautenhahn, K., Kubacki, J., Haegele, M., Parlitz, C., & Alami, R. (2005, August). A methodological approach relating the classification of gesture to identification of human intent in the context of human-robot interaction. In ROMAN 2005. IEEE International Workshop on Robot and Human Interactive Communication, 2005. (pp. 371-377). IEEE.
  45. Neto, P., Simao, M., Mendes, N., & Safeea, M. (2019). Gesture-based human-robot interaction for human assistance in manufacturing. The International Journal of Advanced Manufacturing Technology, 101, 119-135.
  46. Newman, D., Lau, J. H., Grieser, K., & Baldwin, T. (2010, June). Automatic evaluation of topic coherence. In Human language technologies: The 2010 annual conference of the North American chapter of the association for computational linguistics (pp. 100-108).
  47. Onnasch, L., & Roesler, E. (2021). A taxonomy to structure and analyze human-robot interaction. International Journal of Social Robotics, 13(4), 833-849.
  48. Parasuraman, S., & Alutto, J. A. (1984). Sources and outcomes of stress in organizational settings: Toward the development of a structural model. Academy of Management Journal, 27(2), 330-350.
  49. Prentice, C., & Nguyen, M. (2020). Engaging and retaining customers with AI and employee service. Journal of Retailing and Consumer Services, 56, 102186.
  50. Qureshi, S. R., & Gupta, A. (2014, March). Towards efficient big data and data analytics: a review. In 2014 conference on IT in business, industry and government (CSIBIG) (pp. 1-6). IEEE.
  51. Roberts, R. D., Zeidner, M., & Matthews, G. (2007). Emotional intelligence: Knowns and unknowns. The science of emotional intelligence: Knowns and unknowns, 419-474.
  52. Likhitha, S., Harish, B. S., & Kumar, H. K. (2019). A detailed survey on topic modeling for document and short text data. International Journal of Computer Applications, 178(39), 1-9.
  53. Salem, M., Rohlfing, K., Kopp, S., & Joublin, F. (2011, July). A friendly gesture: Investigating the effect of multimodal robot behavior in human-robot interaction. In 2011 ro-man (pp. 247-252). IEEE.
  54. Sanchez-Franco, M. J., & Rey-Moreno, M. (2022). Do travelers' reviews depend on the destination? An analysis in coastal and urban peer-to-peer lodgings. Psychology & marketing, 39(2), 441-459.
  55. Saunderson, S., & Nejat, G. (2019). How robots influence humans: A survey of nonverbal communication in social human-robot interaction. International Journal of Social Robotics, 11, 575-608.
  56. Sen, W., Hong, Z., & Xiaomei, Z. (2022). Effects of human-machine interaction on employee's learning: A contingent perspective. Frontiers in Psychology, 13, 876933.
  57. Shao, M., Snyder, M., Nejat, G., & Benhabib, B. (2020). User affect elicitation with a socially emotional robot. Robotics, 9(2), 44.
  58. Smith, C. (2019). An employee's best friend? How AI can boost employee engagement and performance. Strategic HR Review, 18(1), 17-20. https://doi.org/10.1108/SHR-11-2018-0092
  59. Stede, M., & Patz, R. (2021, August). The climate change debate and natural language processing. In Proceedings of the 1st Workshop on NLP for Positive Impact (pp. 8-18).
  60. Tao, J., & Tan, T. (2005, October). Affective computing: A review. In International Conference on Affective computing and intelligent interaction (pp. 981-995). Berlin, Heidelberg: Springer Berlin Heidelberg.
  61. Trevelyan, J. (1999). Redefining robotics for the new millennium. The International Journal of Robotics Research, 18(12), 1211-1223. https://doi.org/10.1177/02783649922067816
  62. Umamaheswaran, S., Dar, V., Sharma, E., & Kurian, J. S. (2023). Mapping Climate Themes From 2008-2021-An Analysis of Business News Using Topic Models. IEEE Access, 11, 26554-26565.
  63. Vichitkraivin, P., & Naenna, T. (2021). Factors of healthcare robot adoption by medical staff in Thai government hospitals. Health and Technology, 11, 139-151.
  64. Walters, M. L., Dautenhahn, K., Te Boekhorst, R., Koay, K. L., Kaouri, C., Woods, S., ... & Werry, I. (2005, August). The influence of subjects' personality traits on personal spatial zones in a human-robot interaction experiment. In ROMAN 2005. IEEE International Workshop on Robot and Human Interactive Communication, 2005. (pp. 347-352). IEEE.
  65. Zeng, Z., Chen, P. J., & Lew, A. A. (2020). From high-touch to high-tech: COVID-19 drives robotics adoption. Tourism geographies, 22(3), 724-734.
  66. Zhang, T., Su, G., Qing, C., Xu, X., Cai, B., & Xing, X. (2019). Hierarchical lifelong learning by sharing representations and integrating hypothesis. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 51(2), 1004-1014.