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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish
Title of host publicationKEOD 2014 - Proceedings of the International Conference on Knowledge Engineering and Ontology Development
PublisherINSTICC Press
Pages369-375
Number of pages7
ISBN (Print)9789897580499
Publication statusPublished - 2014
Event6th International Conference on Knowledge Engineering and Ontology Development, KEOD 2014 - Rome
Duration: 2014 Oct 212014 Oct 24

Other

Other6th International Conference on Knowledge Engineering and Ontology Development, KEOD 2014
CityRome
Period14/10/2114/10/24

Fingerprint

Social sciences
Support vector machines
Websites
Industry
Personnel
Processing

Keywords

  • Answers to open-ended question
  • Automatic coding system
  • Confidence level
  • Machine learning
  • Natural language processing
  • Occupation and industry coding

ASJC Scopus subject areas

  • Software
  • Information Systems

Cite this

Takahashi, K., Taki, H., Tanabe, S., & 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 KEOD 2014 - Proceedings of the International Conference on Knowledge Engineering and Ontology Development (pp. 369-375). INSTICC Press.

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. / Takahashi, Kazuko; Taki, Hirofumi; Tanabe, Shunsuke; Li, Wei.

KEOD 2014 - Proceedings of the International Conference on Knowledge Engineering and Ontology Development. INSTICC Press, 2014. p. 369-375.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Takahashi, K, Taki, H, Tanabe, S & 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 KEOD 2014 - Proceedings of the International Conference on Knowledge Engineering and Ontology Development. INSTICC Press, pp. 369-375, 6th International Conference on Knowledge Engineering and Ontology Development, KEOD 2014, Rome, 14/10/21.
Takahashi K, Taki H, Tanabe S, Li W. 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 KEOD 2014 - Proceedings of the International Conference on Knowledge Engineering and Ontology Development. INSTICC Press. 2014. p. 369-375
Takahashi, Kazuko ; Taki, Hirofumi ; Tanabe, Shunsuke ; Li, Wei. / 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. KEOD 2014 - Proceedings of the International Conference on Knowledge Engineering and Ontology Development. INSTICC Press, 2014. pp. 369-375
@inproceedings{cd7138fd959d4946829fa8ce6331718a,
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",
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.",
keywords = "Answers to open-ended question, Automatic coding system, Confidence level, Machine learning, Natural language processing, Occupation and industry coding",
author = "Kazuko Takahashi and Hirofumi Taki and Shunsuke Tanabe and Wei Li",
year = "2014",
language = "English",
isbn = "9789897580499",
pages = "369--375",
booktitle = "KEOD 2014 - Proceedings of the International Conference on Knowledge Engineering and Ontology Development",
publisher = "INSTICC Press",

}

TY - GEN

T1 - An automatic coding system with a three-grade confidence level corresponding to the national/international occupation and industry standard

T2 - Open to the public on the web

AU - Takahashi, Kazuko

AU - Taki, Hirofumi

AU - Tanabe, Shunsuke

AU - Li, Wei

PY - 2014

Y1 - 2014

N2 - 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.

AB - 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.

KW - Answers to open-ended question

KW - Automatic coding system

KW - Confidence level

KW - Machine learning

KW - Natural language processing

KW - Occupation and industry coding

UR - http://www.scopus.com/inward/record.url?scp=84909979953&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84909979953&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789897580499

SP - 369

EP - 375

BT - KEOD 2014 - Proceedings of the International Conference on Knowledge Engineering and Ontology Development

PB - INSTICC Press

ER -