@inproceedings{jalilian-etal-2026-enhancing,
title = "Enhancing Job Evaluation with Data Augmentation and Text Classification",
author = "Jalilian, Samaneh and
Weeren, Niels van and
Shokri, Mohammad and
Bijl, Thijmen and
Verberne, Suzan",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.59/",
pages = "872--883",
ISBN = "979-8-89176-394-4",
abstract = "Accurate job grading and evaluation are essential for ensuring fair compensation in Human Resources (HR) planning. In this research, we propose to improve job evaluation by semi-automating a manual, time-consuming, and inconsistent process with text-based classification models. We address three prediction tasks: job title classification, grading, and compensation prediction. For job title classification, we fine-tune a RoBERTa model for classification and use Gemini to generate synthetic job descriptions for rare job titles. For grade and compensation prediction, we compare TF-IDF and transformer-based embeddings (DistilRoBERTa, MPNet, MiniLM) in combination with deep neural networks and tree-based models (Random Forest, XGBoost). We optimize all models using grid search with hyperparameter tuning and cross-validation. The results show that job title classification by RoBERTa with Gemini-generated descriptions works well with an accuracy of about 97{\%}. In our regression experiments, our models get promising results: for grade prediction, a tuned TF-IDF + XGBoost model achieves a mean absolute error (MAE) of 0.185, and for annual salary prediction, MiniLM embeddings with XGBoost get an MAE of {\texteuro}1,587. These findings demonstrate that a semi-automated pipeline can enhance traditional manual processes by boosting consistency, speeding up HR workflows, and reducing biased assessments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jalilian-etal-2026-enhancing">
<titleInfo>
<title>Enhancing Job Evaluation with Data Augmentation and Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samaneh</namePart>
<namePart type="family">Jalilian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niels</namePart>
<namePart type="given">van</namePart>
<namePart type="family">Weeren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Shokri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thijmen</namePart>
<namePart type="family">Bijl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suzan</namePart>
<namePart type="family">Verberne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>Accurate job grading and evaluation are essential for ensuring fair compensation in Human Resources (HR) planning. In this research, we propose to improve job evaluation by semi-automating a manual, time-consuming, and inconsistent process with text-based classification models. We address three prediction tasks: job title classification, grading, and compensation prediction. For job title classification, we fine-tune a RoBERTa model for classification and use Gemini to generate synthetic job descriptions for rare job titles. For grade and compensation prediction, we compare TF-IDF and transformer-based embeddings (DistilRoBERTa, MPNet, MiniLM) in combination with deep neural networks and tree-based models (Random Forest, XGBoost). We optimize all models using grid search with hyperparameter tuning and cross-validation. The results show that job title classification by RoBERTa with Gemini-generated descriptions works well with an accuracy of about 97%. In our regression experiments, our models get promising results: for grade prediction, a tuned TF-IDF + XGBoost model achieves a mean absolute error (MAE) of 0.185, and for annual salary prediction, MiniLM embeddings with XGBoost get an MAE of €1,587. These findings demonstrate that a semi-automated pipeline can enhance traditional manual processes by boosting consistency, speeding up HR workflows, and reducing biased assessments.</abstract>
<identifier type="citekey">jalilian-etal-2026-enhancing</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.59/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>872</start>
<end>883</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Job Evaluation with Data Augmentation and Text Classification
%A Jalilian, Samaneh
%A Weeren, Niels van
%A Shokri, Mohammad
%A Bijl, Thijmen
%A Verberne, Suzan
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F jalilian-etal-2026-enhancing
%X Accurate job grading and evaluation are essential for ensuring fair compensation in Human Resources (HR) planning. In this research, we propose to improve job evaluation by semi-automating a manual, time-consuming, and inconsistent process with text-based classification models. We address three prediction tasks: job title classification, grading, and compensation prediction. For job title classification, we fine-tune a RoBERTa model for classification and use Gemini to generate synthetic job descriptions for rare job titles. For grade and compensation prediction, we compare TF-IDF and transformer-based embeddings (DistilRoBERTa, MPNet, MiniLM) in combination with deep neural networks and tree-based models (Random Forest, XGBoost). We optimize all models using grid search with hyperparameter tuning and cross-validation. The results show that job title classification by RoBERTa with Gemini-generated descriptions works well with an accuracy of about 97%. In our regression experiments, our models get promising results: for grade prediction, a tuned TF-IDF + XGBoost model achieves a mean absolute error (MAE) of 0.185, and for annual salary prediction, MiniLM embeddings with XGBoost get an MAE of €1,587. These findings demonstrate that a semi-automated pipeline can enhance traditional manual processes by boosting consistency, speeding up HR workflows, and reducing biased assessments.
%U https://aclanthology.org/2026.acl-industry.59/
%P 872-883
Markdown (Informal)
[Enhancing Job Evaluation with Data Augmentation and Text Classification](https://aclanthology.org/2026.acl-industry.59/) (Jalilian et al., ACL 2026)
ACL