DOI QR코드

DOI QR Code

Exploratory Research on Automating the Analysis of Scientific Argumentation Using Machine Learning

머신 러닝을 활용한 과학 논변 구성 요소 코딩 자동화 가능성 탐색 연구

  • Received : 2018.02.22
  • Accepted : 2018.04.23
  • Published : 2018.04.30

Abstract

In this study, we explored the possibility of automating the process of analyzing elements of scientific argument in the context of a Korean classroom. To gather training data, we collected 990 sentences from science education journals that illustrate the results of coding elements of argumentation according to Toulmin's argumentation structure framework. We extracted 483 sentences as a test data set from the transcription of students' discourse in scientific argumentation activities. The words and morphemes of each argument were analyzed using the Python 'KoNLPy' package and the 'Kkma' module for Korean Natural Language Processing. After constructing the 'argument-morpheme:class' matrix for 1,473 sentences, five machine learning techniques were applied to generate predictive models relating each sentences to the element of argument with which it corresponded. The accuracy of the predictive models was investigated by comparing them with the results of pre-coding by researchers and confirming the degree of agreement. The predictive model generated by the k-nearest neighbor algorithm (KNN) demonstrated the highest degree of agreement [54.04% (${\kappa}=0.22$)] when machine learning was performed with the consideration of morpheme of each sentence. The predictive model generated by the KNN exhibited higher agreement [55.07% (${\kappa}=0.24$)] when the coding results of the previous sentence were added to the prediction process. In addition, the results indicated importance of considering context of discourse by reflecting the codes of previous sentences to the analysis. The results have significance in that, it showed the possibility of automating the analysis of students' argumentation activities in Korean language by applying machine learning.

본 연구에서는 국내 교육학 연구에서 거의 사용되지 않던 머신 러닝 기술을 과학 교육 연구에 접목하여, 학생들의 과학 논변 활동에서 나타나는 논변의 구성 요소를 분석하는 과정을 자동화할 수 있는 가능성을 탐색해보았다. 학습 데이터로는 Toulmin이 제안하였던 틀에 따라 학생들의 과학 논변 구성 요소를 코딩한 국내 선행 문헌 18건을 수합하고 정리하여 990개의 문장을 추출하였으며, 테스트 데이터로는 실제 교실 환경에서 발화된 과학 논변 전사 데이터를 사용하여 483개의 문장을 추출하고 연구자들이 사전 코딩을 수행하였다. Python의 'KoNLPy' 패키지와 '꼬꼬마(Kkma)' 모듈을 사용한 한국어 자연어 처리(Natural Language Processing, NLP)를 통해 개별 논변을 구성하는 단어와 형태소를 분석하였으며, 연구자 2인과 국어교육 석사학위 소지자 1인의 검토 과정을 거쳤다. 총 1,473개의 문장에 대한 논변-형태소:품사 행렬을 만든 후에 다섯 가지 방법으로 머신 러닝을 수행하고 생성된 예측 모델과 연구자의 사전 코딩을 비교한 결과, 개별 문장의 형태소만을 고려하였을 때에는 k-최근접 이웃 알고리즘(KNN)이 약 54%의 일치도(${\kappa}=0.22$)를 보임으로써 가장 우수하였다. 직전 문장이 어떻게 코딩되어 있는지에 관한 정보가 주어졌을 때, k-최근접 이웃 알고리즘(KNN)이 약 55%의 일치도(${\kappa}=0.24$)를 보였으며 다른 머신 러닝 기법에서도 전반적으로 일치도가 상승하였다. 더 나아가, 본 연구의 결과는 과학 논변 활동의 분석에서 개별문장을 고려하는 단순한 방법이 어느 정도 유용함과 동시에, 담화의 맥락을 고려하는 것 또한 필요함을 데이터에 기반하여 보여주었다. 또한 머신 러닝을 통해 교실에서 한국어로 이루어진 과학 논변 활동을 분석하여 연구자와 교사들에게 유용하게 사용될 수 있는 가능성을 보여준다.

Keywords

References

  1. Baek, J., Jeong, D. H., & Hwang, S. (2014). Issues and effects in developing inquiry-based argumentation task for science teachers: A case of Charles’ law experiment. Journal of the Korean Association for Science Education, 34(2), 79-92. https://doi.org/10.14697/jkase.2014.34.2.0079
  2. Berland, L. K., & Hammer, D. (2012). Framing for scientific argumentation. Journal of Research in Science Teaching, 49(1), 68-94. https://doi.org/10.1002/tea.20446
  3. Booth, W. C., Colomb, G. G., & Williams, J. M. (2008). The craft of research. Chicago: The University of Chicago Press.
  4. Cho, H. -A., Chang, J. -E., & Kim, H. -B. (2013). Epistemic level in middle school students’ small-group argumentation using first-hand or second-hand data. Journal of the Korean Association for Science Education, 33(2), 486-500. https://doi.org/10.14697/jkase.2013.33.2.486
  5. Choi, S. J., & Kim, J. -B. (2017). Comparison analysis of speech recognition open APIs' accuracy. Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, 7(8), 411-418.
  6. Domingos, P. (2015). The master algorithm: How the quest for ultimate learning machine will remake our world. NY: Basic Books.
  7. Driver, R., Newton, P., & Osborne, J. (2000). Establishing the norms of scientific argumentation in classrooms. Science Education, 84(3), 287-312. https://doi.org/10.1002/(SICI)1098-237X(200005)84:3<287::AID-SCE1>3.0.CO;2-A
  8. Duschl, R. (2008). Science education in three-part harmony: Balancing conceptual, epistemic, and social learning goals. Review of Research in Education, 32(1), 268-291. https://doi.org/10.3102/0091732X07309371
  9. Erduran, S., Simon, S., & Osborne, J. (2004). TAPing into argumentation: Developments in the application of Toulmin’s argument pattern for studying science discourse. Science Education, 88(6), 915-933. https://doi.org/10.1002/sce.20012
  10. Fritsch, S., & Guenther, F. (2016). neuralnet: Training of neural networks. R package version 1.33. Retrieved January 3, 2018, from https://CRAN.R-project.org/package=neuralnet
  11. Go, A., Bhayani, R., & Huang, L. (2009). Twitter sentiment classification using distant supervision. CS224N Project Report, Stanford.
  12. Go, I. -K. (2016). The key concept study of agriculture unit in practical arts based on big data analysis methods. Journal of Learner-Centered Curriculum and Instruction, 16(4), 431-450.
  13. Goodman, B. A., Linton, F. N., Gaimari, R. D., Hitzeman, J. M., Ross, H. J., & Zarrella, G. (2005). Using dialogue features to predict trouble during collaborative learning. User Modeling and User-Adapted Interaction, 15(1), 85-134. https://doi.org/10.1007/s11257-004-5269-x
  14. Han, H. -J., Lee, T., Ko, H., Lee, S. -K., Kim, E., Choe, S. -U., & Kim, C. -J. (2012). An analysis of the type of rebuttal in argumentation among science-gifted student. Journal of the Korean Association for Science Education, 32(4), 717-728. https://doi.org/10.14697/jkase.2012.32.4.717
  15. Heo, H., Yang, E. -J., Kim, D., Choi, J. G., & Moon, Y. S. (2017). Human intelligence and learning in the era of artificial intelligence. The Korean Journal of Philosophy of Education, 39(1), 101-132. https://doi.org/10.15754/jkpe.2017.39.1.005
  16. Ivezic, Z., Connolly, A. J., VanderPlas, J. T., & Gray, A. (2014). Statistics, data mining, and machine learning in astronomy: A practical Python guide for the analysis of survey data. NJ: Princeton University Press.
  17. Jang, G. -H. (2003). A trial on restruction of written language/spoken language and their styles. Korean Semantics, 13, 143-165.
  18. Jeon, H. (2016). KoNLP: Korean NLP package. R package version 0.80.1. Retrieved January 3, 2018, from https://CRAN.R-project.org/package=KoNLP.
  19. Jimenez-Aleixandre, M., Rodriguez, A. B., & Duschl, R. A. (2000). "Doing the lesson" or "doing science": Argument in high school genetics. Science Education, 84(6), 757-792. https://doi.org/10.1002/1098-237X(200011)84:6<757::AID-SCE5>3.0.CO;2-F
  20. Jung, C. Y., & Seo, Y. H. (1998). Artificial intelligence: machine translation of Korean-to-English spoken language based on semantic patterns. The KIPS Transactionsty, 5(9), 2361-2368.
  21. Karatzoglou A., Smola A., Hornik, K., & Zeileis, A. (2004). kernlab - An S4 package for kernel methods in R. Journal of Statistical Software 11(9), 1-20. Retrieved January 3, 2018, from http://www.jstatsoft. org/v11/i09/
  22. Kim, I. -H. (2003). The nature of context and its relations to language use. English Language Education, 26, 7-34.
  23. Kim, K., & Park, Y. (2017). Development and application of the teaching and learning model of artificial intelligence education for elementary students. Journal of The Korean Association of Information Education, 21(1), 137-147. https://doi.org/10.14352/jkaie.21.1.137
  24. Kwon, J. -S., & Kim, H. -B. (2016). Exploring small group argumentation shown in designing an experiment: Focusing on students’ epistemic goals and epistemic considerations for activities. Journal of the Korean Association for Science Education, 36(1), 45-61. https://doi.org/10.14697/jkase.2016.36.1.0045
  25. Lantz, B. (2013). Machine learning with R. Packt Publishing Ltd.
  26. Larrain, A., Freire, P., & Howe, C. (2014). Science teaching and argumentation: One-sided versus dialectical argumentation in Chilean middle-school science lessons. International Journal of Science Education, 36(6), 1017-1036. https://doi.org/10.1080/09500693.2013.832005
  27. Lederman, N. G. (1992). Students' and teachers' conceptions of the nature of science: A review of the research. Journal of Research in Science Teaching, 29, 331-359. https://doi.org/10.1002/tea.3660290404
  28. Lee, D., Yeon, J., Hwang, I., & Lee, S. (2010). KKMA: A tool for utilizing sejong corpus based on relational database. Journal of KIISE: Computing Practices and Letters, 16(11), 1046-1050.
  29. Lee, E. J., Yun, S. M., & Kim, H. -B. (2015). Exploring small group argumentation and epistemological framing of gifted science students as revealed by the analysis of their responses to anomalous data. Journal of the Korean Association for Science Education, 35(3), 419-429. https://doi.org/10.14697/jkase.2015.35.3.0419
  30. Lee, J., & Kim, H. -B. (2011). Small group argumentation pattern of middle school students constructed in the conflict context. Biology Education, 39(2), 235-247. https://doi.org/10.15717/bioedu.2011.39.2.235
  31. Lee, J., Nam, C., & Shin, D. (2017). Machine learning bigdata education platform using apache spark. Proceedings of the Korea Software Congress 2017.
  32. Lee, J. -A., Maeng, S. -H., & Kim, C. -J. (2008). A new way of reading the science classroom discourse: Pedagogical discourse analysis. Journal of the Korean Association for Science Education, 28(8), 832-847.
  33. Lee, J. -S., Kang, K. -H., & Lee, S. -K. (2005). Students’ interactions of reasoning and inductions in small group science discussion. The Journal of the Smeieccu, 26(1), 91-112.
  34. Lee, K. H., Yun, S. -M., & Kim, H. -B. (2012). Understanding of middle school students’ small group argumentation of plant and animal classification: Focusing on the effects of leader. Biology Education, 40(10), 71-86. https://doi.org/10.15717/bioedu.2012.40.1.71
  35. Lee, S., Kim, H. -J., & Jung, S. (2016). Text-mining based topic analysis on online sexism. Journal of Cybercommunication Academic Society 33(3), 159-199.
  36. Lee, S., Lee, C., & Lee, G. (2010). Example-based dialog system for english conversation tutoring. Journal of KISS : Software and Applications, 37(2), 129-136.
  37. Lee, S., Park, S. -H., & Kim, H. -B. (2016). Exploring secondary students’ progression in group norms and argumentation competency through collaborative reflection about small group argumentation. Journal of the Korean Association for Science Education, 36(6), 895-910. https://doi.org/10.14697/jkase.2016.36.6.0895
  38. Lee, S. -K. (2006). The patterns and the characteristics of students’ interactive argumentation in the small-group discussions. Journal of the Korean Chemical Society, 50(1), 79-88. https://doi.org/10.5012/jkcs.2006.50.1.079
  39. Lee, Y., Lee, S., & Kim, H. -B. (2015). Understanding students’ knowledge construction and scientific argumentation according to the level of openness in inquiry and the abstraction level of scientific knowledge. Biology Education, 43(1), 50-69. https://doi.org/10.15717/bioedu.2015.43.1.50
  40. Lee, Y. -O. (2002). Translation problems between Korean and English reflecting their structural differences: With respect to the translation of reported speech. The Journal of Translation Studies, 3(1), 59-81.
  41. Lim, D. (2011). Sentence types in Korean. Journal of Korean Linguistics, 60(4), 323-359.
  42. Lim, D. (2015). Bigdata analysis using R. Paju: Freeacademy.
  43. Lim, J., Song, Y. -M., Song, M., & Yang, I. -H. (2010). An analysis on the level of elementary gifted students’ argumentation in scientific inquiry. Journal of Korean Elementary Science Education, 29(4), 441-450.
  44. Lim, H., & Yeo, S. -I. (2012). Characteristics on elementary students' argumentation in science problem solving process. Journal of Korean Elementary Science Education, 31(1), 13-24.
  45. Luckin, R., Holmes, W., Griffiths, M., & Forcier, L. B. (2016). Intelligence unleashed: An argument for AI in education. London: Pearson..
  46. Maeng, S., Park, Y. -S., & Kim, C. -J. (2013). Methodological review of the research on argumentative discourse focused on analyzing collaborative construction and epistemic enactments of argumentation. Journal of the Korean Association for Science Education, 33(4), 840-862. https://doi.org/10.14697/jkase.2013.33.4.840
  47. Meyer, D., Dimitriadou, E., Hornik, K., Weingessel, A., & Leisch, F. (2017). e1071: Misc functions of the department of statistics, probability theory group (formerly: E1071), TU Wien. R package version 1.6-8. Retrieved January 3, 2018, from https://CRAN.R-project.org/package=e1071
  48. McAlister, S., Allen, C., Ravenscroft, A., Reed, C., Bourget, D., Lawrence, J., Borner, K., & Light, R. (2014). From big data to argument analysis and automated extraction: A selective study of argument in the philosophy of animal psychology from the volumes of the hathi trust collection. Final Report. Digging into Data.
  49. McNeill, K. L. (2009). Teachers' use of curriculum to support students in writing scientific arguments to explain phenomena. Science Education, 93(2), 233-268. https://doi.org/10.1002/sce.20294
  50. McNeill, K. L., & Krajcik, J. (2007). Middle school students' use of appropriate and inappropriate evidence in writing scientific explanations. Thinking with Data, 233-265.
  51. Ministry of Education (MOE) (2015). 2015 revised science curriculum. Ministry of Education 2015-74 [issue 9].
  52. Nielsen, J. A. (2013). Dialectical features of students’ argumentation: A critical review of argumentation studies in science education. Research in Science Education, 43(1), 371-393. https://doi.org/10.1007/s11165-011-9266-x
  53. Oh, J. A., Lee, S. -K., & Kim, C. -J. (2008). A case study on scientific inquiry and argumentative communication in earth science MBL classes. Journal of the Korean Earth Science Society, 29(2), 189-203. https://doi.org/10.5467/JKESS.2008.29.2.189
  54. Ok, J. -S. (2004). A study on the prospect of using speech recognition softwares in elementary English education, STEM Journal, 5(2), 65-82.
  55. Osborne, J., Erduran, S., & Simon, S. (2004). Enhancing the quality of argumentation in school science. Journal of Research in Science Teaching, 41(10), 994-1020. https://doi.org/10.1002/tea.20035
  56. Paik, S. H., & Son, S. H. (2014). An analysis of pre-service science teachers' argument structures, the factors affecting the practice of state change experiment in 7th grade and cognition of pre-service education. Journal of the Korean Association for Science Education, 34(3), 197-206. https://doi.org/10.14697/jkase.2014.34.3.0197
  57. Pardo, A. (2014). Designing learning analytics experiences. In J. A. Larusson & B. White (Eds.), Learning analytics: From research to practice (pp. 15-38). NY: Springer.
  58. Park, E. L., & Cho, S. (2014). KoNLPy: Korean natural language processing in Python. Proceedings of the 26th Annual Conference on Human & Cognitive Language Technology, Chuncheon, Korea, Oct 2014.
  59. Park, J. H., & Shin, N. M. (2017). Student’s perceptions of artificial intelligence technology and artificial intelligence teachers. The Journal of Korean Teacher Education, 34(2), 169-192
  60. Park, S. -K. (2015). Analysis on the argumentation pattern and level of students' mental models in modeling-based learning about geologic structures. Journal of the Korean Association for Science Education, 35(5), 919-929. https://doi.org/10.14697/jkase.2015.35.5.0919
  61. Ripley, B. (2016). tree: Classification and regression trees. R package version 1.0-37. Retrieved January 3, 2018, from https://CRAN.R-project.org/package=tree
  62. Rosé, C., Wang, Y. -C., Cui, Y., Arguello, J., Stegmann, K., Weinberger, A., & Fischer, F. (2008). Analyzing collaborative learning processes automatically: Exploiting the advances of computational linguistics in computer-supported collaborative learning. Computer-Supported Collaborative Learning, 3, 237-271. https://doi.org/10.1007/s11412-007-9034-0
  63. Sampson, V., & Blanchard, M. R. (2012). Science teachers and scientific argumentation: Trends in views and practice. Journal of Research in Science Teaching, 49(9), 1122-1148. https://doi.org/10.1002/tea.21037
  64. Sampson, V., & Clark, D. B. (2008). Assessment of the ways students generate arguments in science education: Current perspectives and recommendations for future directions. Science Education, 92(3), 449-472.
  65. Sampson, V., & Schleigh, S. (2013). Scientific argumentation in biology: 30 classroom activities. Arlington, VA: NSTA Press.
  66. Scheuer, O., McLaren, B. M., Loll, F., & Pinkwart, N. (2012). Automated analysis and feedback techniques to support and teach argumentation: A survey. In N. Pinkwart & B. M. McLaren (Eds.), Educational technologies for teaching argumentation skills (pp. 71-124). Bentham Books.
  67. Shin, H. S., & Kim, H. -J. (2011). Development of the analytic framework for dialogic argumentation using the TAP and a diagram in the context of learning the circular motion. Journal of the Korean Association for Science Education, 32(5), 1007-1026. https://doi.org/10.14697/jkase.2012.32.5.1007
  68. Shin, S., Ha, M., & Lee, J. -K. (2017). High school students’ perception of artificial intelligence: Focusing on conceptual understanding, emotion and risk perception. Journal of Learner-Centered Curriculum and Instruction, 17(21), 289-312.
  69. Simon, S., Erduran, S., & Osborne, J. (2006). Learning to teach argumentation: Research and development in the science classroom. International Journal of Science Education, 28(2-3), 235-260. https://doi.org/10.1080/09500690500336957
  70. Sionti, M., Ai, H., Rosé, C. P., & Resnick, L. (2011). A framework for analyzing development of argumentation through classroom discussions. Educational technologies for teaching argumentation skills, 28-55.
  71. Soller, A. (2004). Computational modeling and analysis of knowledge sharing in collaborative distance learning. User Modeling and User-Adapted Interaction, 14(4), 351-381. https://doi.org/10.1023/B:USER.0000043436.49168.3b
  72. Toulmin, S. (1958). The uses of argument. Cambridge: Cambridge University Press.
  73. Venables, W. N. & Ripley, B. D. (2002) Modern applied statistics with S (4th ed.). NY: Springer.
  74. Wee, S., Yoon, J., & Lim, S. (2014). An analysis on argumentation structure development of preservice teachers through argumentative writing on earth science related SSI. Journal of the Korean Society of Earth Science Education, 7(1), 11-23. https://doi.org/10.15523/JKSESE.2014.7.1.011
  75. Won, H. -Y. (2011). A study on the colloquial final ending '-잖아(요)' for Korean language education. Korean Language & Literature, 79, 307-327.
  76. Williams, J. M., & Colomb, G. G. (2007). The craft of argument. Pearson Education.
  77. Yu, Y. -L., & Baek, S. -G. (2016). Issue analysis of the related mass media’s news articles on the 2015 revised national curriculum using automated text analysis. The Journal of Curriculum and Evaluation, 19(3), 127-156.
  78. Zhang, B. -T. (2017). Deep learning. Seoul: Hongrung Publishing Company.
  79. Zhao, M. (2016). A study for the adverb postpositions of 'ey', 'eyse' in the Korean language: Focused 'ey', 'eyse'. Studies in Linguistics, 40(7), 337-359.

Cited by

  1. 온라인 학습에서 머신러닝을 활용한 초등 4학년 식물 분류 학습의 적용 사례 연구 vol.40, pp.1, 2018, https://doi.org/10.15267/keses.2021.40.1.66
  2. 기계 학습을 활용한 논증 수준 자동 채점 및 논증 패턴 분석 vol.41, pp.3, 2018, https://doi.org/10.14697/jkase.2021.41.3.203