Automatically Detecting Errors in Employer Industry Classification Using Job Postings

Abstract

In the recruitment domain, knowing the employer industry of jobs is important to get an insight about the demand in each industry. The existing system at CareerBuilder uses an employer name normalization system and an employer knowledge base (KB) to infer the employer industry of a job. However, errors may occur during the computation of the job employer and in the construction of the employer KB with the industry attributes. Since the KB is huge, it is not possible to manually detect the errors. Therefore, in this paper we use machine learning techniques to automatically detect the errors. With the observation that the main jobs posted by an employer often relate to the employer industry, e.g., truck driver jobs often correspond to employers in the transportation industry, we develop a system that classifies the industry of an employer using job posting data. We aggregate job postings from an employer and derive features from employer names, employer descriptions, job titles, and job descriptions to predict the industry of the employer. Two models are used for classification:(1) support vector machine and (2) random forest. Our experiments show that random forest is more effective than SVM in identifying the errors in the existing industry classification system, which achieves precision 0.69, recall 0.78, and f-score 0.73. It especially better handles mixed feature vectors when normalization errors occur. We also observe that generally our models perform better in detecting errors for industries that have higher error rates.

Identifying essential nonprofits with a novel NLP Method

“…The IRS Determination Specialists are humans coding tax exempt entities using the hierarchical NTEE code scheme (Jones, 2019). Automatic classification has been used to find errors in human classification entries by examining text descriptions (Chern et al, 2018) and by applying existing hierarchies (NTEE codes) to text to evaluate how to improve that classification system (Ma et al, 2021).…”

A Novel Stream Mining Approach as Stream-Cluster Feature Tree Algorithm: A Case Study in Turkish Job Postings

“…In [23], text mining analysis of job postings in the field of librarianship was conducted, and the basic competencies in this field were revealed. It can be found that clustering algorithms are used predominantly for text mining analysis [24,25], even if classification algorithms are used to create general prediction models [26] or specific models, such as those for detecting errors in job postings [27]. Studies have utilized clustering methods for job postings associated with various occupational groups, such as those in the accounting [28], health [29], art [30], engineering [31], and education [32] fields.…”