JMIR Publications

ABSTRACT

Background:

Although injured employees are legally covered by worker's compensation insurance in South Korea, some employers make agreements to prevent the injured employees from covering their compensation. Thus, this leads to under-reporting of occupational injury statistics. Illegal compensation (in Korean called “gong-sang”) is a critical way to underreport or cover-up. However, “gong-sang” is not counted as official occupational injury statistics and so we cannot identify the “gong-sang”-related issues.

Objective:

This study analyzed the social media data using topic modeling to explore hidden knowledge about illegal compensation - “gong-sang” - for occupational injury in South Korea.

Methods:

We collected a total of 2,210 documents from social media data by filtering the keyword “gong-sang”. The study period was between January 1, 2006 and December 31, 2017. After natural language processing of the Korean language using KoNLPy, a morphological analyzer, we performed topic modeling by the Latent Dirichlet allocation (LDA) in the Python library, Gensim. A 10-topic model was selected and ran with 3000 Gibbs sampling iterations to fit the model.

Results:

LDA model was classified gong-sang related documents into four categories from a total of 10 topics. Topic 1 was the greatest concern (60.5%). Workers who suffered from industrial accidents seemed to be worried about illegal compensation and legal insurance claims, wherein keywords on the choice between illegal compensation and legal insurance claims were included. In Topic 2, keywords were associated with claims for industrial accident insurance benefits. Topics 3 and 4, as the second-highest concern (19.2%) contained keywords implying the monetary compensation of “gong-sang”. The rest topics (Topics 5-10) included keywords on vulnerable job (i.e., workers at construction and defense industry, delivery riders, and foreign workers) and body parts (i.e., injuries to hands, face, teeth, lower limbs, and back) to “gong-sang”.

Conclusions:

We explored hidden knowledge to identify the salient issues surrounding “gong-sang” using LDA model. These topics may provide valuable information to ensure the more efficient operation of South Korea’s occupational health and safety administration, and protect vulnerable workers from illegal “gong-sang” compensation practices.