Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Formative Research

Date Submitted: Sep 27, 2019
Open Peer Review Period: Sep 27, 2019 - Nov 10, 2019
Date Accepted: Jun 14, 2020
(closed for review but you can still tweet)

The final, peer-reviewed published version of this preprint can be found here:

Occupation Coding of Job Titles: Iterative Development of an Automated Coding Algorithm for the Canadian National Occupation Classification (ACA-NOC)

Bao H, Baker CJ, Adisesh A

Occupation Coding of Job Titles: Iterative Development of an Automated Coding Algorithm for the Canadian National Occupation Classification (ACA-NOC)

JMIR Form Res 2020;4(8):e16422

DOI: 10.2196/16422

PMID: 32755893

PMCID: 7439137

ACA-NOC: Development of an Automated Coding Algorithm for the Canadian National Occupation Classification

  • Hongchang Bao; 
  • Christopher JO Baker; 
  • Anil Adisesh

ABSTRACT

Background:

In many community-based research studies, occupational information is needed to augment existing data sets. Such information is usually solicited during interviews with open-ended questions, like “what is your job?” and “what industry sector do you work in?” Before being able to use this information for further analysis, the responses need to be categorized using a coding system , like the Canadian National Occupational Classification (NOC). This is typically carried out by manual coding, which is a time-consuming and error prone activity, suitable for automation.

Objective:

To facilitate automated coding we proposed to introduce a robust algorithm that is able to identify the NOC (2016) codes using only a job title and supplemented by industry information as input. Using manually coded data sets we sought to benchmark and iteratively improve the performance of the algorithm.

Methods:

We developed the ASOC (Automated Semantic Occupation Coding) algorithm, based on the National Occupational Classification (NOC) 2016, which allows users to match NOC codes with job titles and industry titles. We employed several different search strategies in the ASOC algorithm to find the best match, including: Exact Search, Minor Exact Search, Like Search, Near (same order) Search, Near (different order) Search, Any Search, Weak Match Search. In addition, Bayes rule was applied in the algorithm to choose the best matching codes.

Results:

ASOC was applied to 500 manually coded job titles and industry titles. The accuracy rate at the 4-digit NOC code level was 58.66% and improved when broader job-categories were considered (65.01% at the 3-digit NOC code level, 72.26% at the 2-digit NOC code level, 81.63% at the 1-digit NOC code level).

Conclusions:

ASOC is a robust algorithm for automatically coding to the Canadian National Occupational Classification system, and has been evaluated using real world data. It allows researchers to codify data by occupation in a timely and cost-efficient manner, so that further analytics are possible.


 Citation

Please cite as:

Bao H, Baker CJ, Adisesh A

Occupation Coding of Job Titles: Iterative Development of an Automated Coding Algorithm for the Canadian National Occupation Classification (ACA-NOC)

JMIR Form Res 2020;4(8):e16422

DOI: 10.2196/16422

PMID: 32755893

PMCID: 7439137

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.