An Exploratory Approach to Discovering Salary-Related Wording in Job Postings in Korea

  • Ha, Taehyun (Future Technology Analysis Center, Korea Institute of Science and Technology Information (KISTI)) ;
  • Coh, Byoung-Youl (Future Technology Analysis Center, Korea Institute of Science and Technology Information (KISTI)) ;
  • Lee, Mingook (Future Technology Analysis Center, Korea Institute of Science and Technology Information (KISTI)) ;
  • Yun, Bitnari (Center for Research and Development Investment and Strategy Research, Korea Institute of Science and Technology Information (KISTI)) ;
  • Chun, Hong-Woo (Future Technology Analysis Center, Korea Institute of Science and Technology Information (KISTI))
  • Received : 2022.04.22
  • Accepted : 2022.05.17
  • Published : 2022.06.20


Online recruitment websites discuss job demands in various fields, and job postings contain detailed job specifications. Analyzing this text can elucidate the features that determine job salaries. Text embedding models can learn the contextual information in a text, and explainable artificial intelligence frameworks can be used to examine in detail how text features contribute to the models' outputs. We collected 733,625 job postings using the WORKNET API and classified them into low, mid, and high-range salary groups. A text embedding model that predicts job salaries based on the text in job postings was trained with the collected data. Then, we applied the SHapley Additive exPlanations (SHAP) framework to the trained model and discovered the significant words that determine each salary class. Several limitations and remaining words are also discussed.



  1. Alvarez-Melis, D., & Jaakkola, T. S. (2018). On the robustness of interpretability methods. arXiv.
  2. Antenucci, D., Cafarella, M., Levenstein, M., Re, C., & Shapiro, M. D. (2014). Using social media to measure labor market flows.
  3. Bach, S., Binder, A., Montavon, G., Klauschen, F., Muller, K. R., & Samek, W. (2015). On pixel-wise explanations for nonlinear classifier decisions by layer-wise relevance propagation. PloS One, 10(7), e0130140.
  4. Borisyuk, F., Zhang, L., & Kenthapadi, K. (2017, August 13-17). LiJAR: A system for job application redistribution towards efficient career marketplace. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1397-1406). ACM.
  5. Chang, H. C., Wang, C. Y., & Hawamdeh, S. (2019). Emerging trends in data analytics and knowledge management job market: Extending KSA framework. Journal of Knowledge Management, 23(4), 664-686.
  6. Chen, J., Koju, W., Xu, S., & Liu, Z. (2021, March 26-28). Sales forecasting using deep neural network and SHAP techniques. Proceedings of the 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE) (pp. 135-138). IEEE.
  7. Chen, T., Xu, J., Ying, H., Chen, X., Feng, R., Fang, X., Gao, H., & Wu, J. (2019). Prediction of extubation failure for intensive care unit patients using light gradient boosting machine. IEEE Access, 7, 150960-150968.
  8. Choi, I. H., Kim, Y. S., & Lee, C. K. (2020, September 17-19). A study of the classification of IT jobs using LSTM and LIME. Proceedings of the 9th International Conference on Smart Media and Applications (pp. 248-252). ACM.
  9. Clark, K., Luong, M. T., Le, Q. V., & Manning, C. D. (2020). ELECTRA: Pre-training text encoders as discriminators rather than generators. arXiv.
  10. Daneva, M., Wang, C., & Hoener, P. (2017, November 9-10). What the job market wants from requirements engineers? An empirical analysis of online job ads from the Netherlands. Proceedings of the 11th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (pp. 448-453). IEEE.
  11. Gunning, D. (2017). Explainable artificial intelligence (XAI). Defense Advanced Research Projects Agency (DARPA).
  12. Ha, T., Lee, M., Yun, B., & Coh, B. Y. (2022). Job forecasting based on the patent information: A word embedding-based approach. IEEE Access, 10, 7223-7233.
  13. Hirudayaraj, M., & Baker, R. (2018). HRD competencies: Analysis of employer expectations from online job postings. European Journal of Training and Development, 42(9), 577-596.
  14. Karakatsanis, I., AlKhader, W., MacCrory, F., Alibasic, A., Omar, M. A., Aung, Z., & Woon, W. L. (2017). Data mining approach to monitoring the requirements of the job market: A case study. Information Systems, 65, 1-6.
  15. Kaya, M., & Bogers, T. (2021, September 27-October 1). Effectiveness of job title based embeddings on resume to job ad recommendation. Proceedings of the 2021 Workshop on Recommender Systems for Human Resources, RECSYS IN HR 2021 (pp. 1-7). CEUR Workshop Proceedings.
  16. Ku, D. (2021). Social recruiting: Everything you need to know for 2022.
  17. Lacic, E., Reiter-Haas, M., Duricic, T., Slawicek, V., & Lex, E. (2019, September 16-20). Should we embed? A study on the online performance of utilizing embeddings for real-time job recommendations. Proceedings of the 13th ACM Conference on Recommender Systems (pp. 496-500). ACM.
  18. Lundberg, S. M., & Lee, S. I. (2017, December 4-9). A unified approach to interpreting model predictions. In I. Guyon, U. von Luxburg, S. Bengio, H. M. Wallach, R. Fergus, S. V. N. Vishwanathan, & R. Garnett (Eds.), Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems (pp. 4768-4777). NIPS.
  19. Park, J. (2020). KoELECTRA: Pretrained ELECTRA model for Korean.
  20. Park, J. H., Jo, H. S., Lee, S. H., Oh, S. W., & Na, M. G. (2022). A reliable intelligent diagnostic assistant for nuclear power plants using explainable artificial intelligence of GRU-AE, LightGBM and SHAP. Nuclear Engineering and Technology, 54, 1271-1287.
  21. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016, August 13-17). "Why should I trust you?": Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135-1144). ACM.
  22. Scrivner, O., Nguyen, T., Simon, K., Middaugh, E., Taska, B., & Borner, K. (2020). Job postings in the substance use disorder treatment related sector during the first five years of Medicaid expansion. PloS One, 15(1), e0228394.
  23. Sun, Y., Zhuang, F., Zhu, H., Zhang, Q., He, Q., & Xiong, H. (2021). Market-oriented job skill valuation with cooperative composition neural network. Nature Communications, 12(1), 1992.
  24. Ward, I. R., Wang, L., Lu, J., Bennamoun, M., Dwivedi, G., & Sanfilippo, F. M. (2021). Explainable artificial intelligence for pharmacovigilance: What features are important when predicting adverse outcomes? Computer Methods and Programs in Biomedicine, 212, 106415.
  25. Zhao, J., Wang, J., Sigdel, M., Zhang, B., Hoang, P., Liu, M., & Korayem, M. (2021). Embedding-based recommender system for job to candidate matching on scale. arXiv.
  26. Zhu, C., Zhu, H., Xiong, H., Ding, P., & Xie, F. (2016, August 13-17). Recruitment market trend analysis with sequential latent variable models. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 383-392). ACM.