An Automatic Coding System with a Three-Grade Confidence Level Corresponding to the National/International Occupation and Industry Standard - Open to the Public on the Web

Kazuko Takahashi, Hirofumi Taki, Shunsuke Tanabe, Wei Li

2014

Abstract

We develop a new automatic coding system with a three-grade confidence level corresponding to each of the national/international standard code sets for answers to open-ended questions regarding to respondent’s occupation and industry in social surveys including a national census. The “occupation and industry coding” is a necessary task for statistical processing. However, this task requires a great deal of labor and time-consuming. In addition, inconsistent results occur if the coders are not experts of coding. In formal research, various automatic coding systems have been developed, which are incomplete and generally unfriendly to a non-developer user. Our new system assigns three candidate codes to an answer for coders by SVMs (Support Vector Machines), and attaches a three-grade confidence level to the first-ranked predicted code by using classification scores to support a manual check of the results. The system is now open to the public through the Website of the Social Science Japan Data Archive (SSJDA). After the submitted data file which followed the specified format is approved, the users can obtain files of codes for up to four kinds with a three-grade confidence level. In this paper, we describe our system and evaluate it.

References

  1. Hara, J., 1984. Social surveys seminar, University of Tokyo Press.
  2. ISCO, 1988.
  3. http://www.ilo.org/public/english/bureau/stat/isco/isco 88/ (accessed June 19, 2014)
  4. ISIC, 1988.
  5. https://unstats.un.org/unsd/cr/registry/regcst.asp?Cl=2 (accessed June 19, 2014)
  6. Iwai, N., Yasuda, T. (eds.), 2011. Family values in East Asia: A comparison among Japan, South Korea, China, and Taiwan based on East Asian Social Survey 2006, Nakanishiya Shuppan. Kyoto.
  7. Japanese Association of social research, 2011. The special issue on difficulty and potential in cross-national survey research. Advances in social research No.7, Yuhikaku Publishing. Tokyo.
  8. Joachims, T., 1998. Text categorization with Support Vector Machines: Learning with many relevant features. In Proceedings of the European Conference on Machine Learning, 137-142.
  9. Jonsson, J. O. et al., 2009. Microclass mobility: Social reproduction in four countries. American Journal of Sociology 114(4), 977-1036.
  10. Jung, Y., et al., 2008. A web-based automated system for industry and occupation coding. In Proceedings of the Ninth International Conference on Web Information Systems Engineering, 443-457.
  11. Kressel, U., 1999. Pairwise classification and support vector machines. Scholkopf, B., et al. (eds.), Advances in kernel methods support vector learning, 255-268. The MIT Press.
  12. Kurohashi, S., Nagao, M., 1998. Japanese morphological analysis system JUMAN version 3.61, Kyoto University.
  13. NIOCCS, 2013. http://wwwn.cdc.gov/niosh-nioccs/ (accessed June 19, 2014)
  14. Sebastiani, F., 2002. Machine learning automated text categorization. ACM Computing Surveys 34(1), 1-47.
  15. Seiyama, K., 2004. Social surveys, Yuhikaku Publishing. Tokyo.
  16. SOIC, 2000. http://www.cdc.gov/niosh/soic/default.html (accessed June 19, 2014)
  17. SSJDA, 2013. http://ssjda.iss.u-tokyo.ac.jp/joint/autocode/ (accessed June 19, 2014)
  18. Takahashi, K., 2000. A supporting system for coding of the answers from an open-ended question: An automatic coding system for SSM occupational data by case frame. Sociological theory and methods 15(1), 149-164.
  19. Takahashi, K., 2002. An applying the automatic occupational/industrial coding system to JGSS-2000. Institute of Regional Studies, Osaka University of Commerce and Institute of Social Science, University of Tokyo (eds.), JGSS Monographs No.1, 171-184.
  20. Takahashi, K., 2003. Applying the automatic occupational/industrial coding system to JGSS-2001. Institute of Regional Studies, Osaka University of Commerce, and Institute of Social Science, University of Tokyo (eds.), JGSS Monographs No.2, 179-191.
  21. Takahashi, K., et al., 2005a. Classification of responses to open-ended questions with machine learning and hand-crafted rules: Automatic occupation coding methods. Sociological theory and methods 19(2), 177-196.
  22. Takahashi, K., et al., 2005b. Automatic occupation coding with combination of machine learning and hand-crafted rules. Lecture Notes in Artificial Intelligence Vol.3518, 269-279. Springer. Heidelberg.
  23. Takahashi, K., et al., 2005c. Applying the occupation coding supporting system for coders (NANACO) in JGSS-2003. Institute of Regional Studies, Osaka University of Commerce and Institute of Social Science, University of Tokyo (eds.), JGSS Monographs No.4, 225-241.
  24. Takahashi, K., 2008. Automatic ISCO-88 coding with machine learning. 2005SSM survey series1 Problem in measurement and analysis in social surveys, 47-68. 2005SSM Survey Research Group.
  25. Takahashi, K. et al., 2008. Direct estimation of classmembership probabilities for multiclass classification using multiple scores. Knowledge and Information System 19(2), 185-210. Springer. London.
  26. Tanabe, S., Aizawa, S., 2008. University of Tokyo Institute of Social Science panel survey discussion paper series: An introduction manual and coding procedures for occupational and industrial coding system, Institute of Social Science, University of Tokyo.
  27. Todoroki, M., Sugino, I., 2013. An introduction to social research methods, Horitsu Bunkasha. Kyoto.
  28. Vapnik, V., 1998. Statistical learning theory, Wiley. New York.
Download


Paper Citation


in Harvard Style

Takahashi K., Taki H., Tanabe S. and Li W. (2014). An Automatic Coding System with a Three-Grade Confidence Level Corresponding to the National/International Occupation and Industry Standard - Open to the Public on the Web . In Proceedings of the International Conference on Knowledge Engineering and Ontology Development - Volume 1: KEOD, (IC3K 2014) ISBN 978-989-758-049-9, pages 369-375. DOI: 10.5220/0005131703690375


in Bibtex Style

@conference{keod14,
author={Kazuko Takahashi and Hirofumi Taki and Shunsuke Tanabe and Wei Li},
title={An Automatic Coding System with a Three-Grade Confidence Level Corresponding to the National/International Occupation and Industry Standard - Open to the Public on the Web},
booktitle={Proceedings of the International Conference on Knowledge Engineering and Ontology Development - Volume 1: KEOD, (IC3K 2014)},
year={2014},
pages={369-375},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005131703690375},
isbn={978-989-758-049-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Knowledge Engineering and Ontology Development - Volume 1: KEOD, (IC3K 2014)
TI - An Automatic Coding System with a Three-Grade Confidence Level Corresponding to the National/International Occupation and Industry Standard - Open to the Public on the Web
SN - 978-989-758-049-9
AU - Takahashi K.
AU - Taki H.
AU - Tanabe S.
AU - Li W.
PY - 2014
SP - 369
EP - 375
DO - 10.5220/0005131703690375