Structure aware models improve job experience level classification accuracy
Evaluating Modeling Approaches for Experience-Level Classification in Job Description
Computation and Language
Summary
The paper looks at how to automatically figure out what experience level a job listing is looking for, like entry-level or senior, by reading the job description text. The authors found that job postings usually have sections, like titles and requirements, that carry important clues about experience. They designed a method that pays special attention to these sections and showed it works better than standard text analysis approaches. They also tested powerful language models and found the structured approach helps especially when job titles don’t clearly say the experience needed.
What this means in practice
- •For recruitment software developers: Integrate structure-aware models to better predict required experience levels in job postings and enhance candidate matching.
- •For hr analytics teams: Use improved experience classification to analyze hiring trends and tailor job ad strategies based on clearer experience requirements.
Tested on one dataset.
Authors
Celia Liang, Eddie Wu, Shiqi Wang, Yonah You
Abstract
This paper investigates the task of predicting job experience levels in recruitment texts, aiming to automatically identify the qualifications required for positions. Unlike traditional text classification, recruitment texts typically possess explicit internal structures, with different paragraphs playing disproportionate roles in conveying experience clues. To address this, we propose a structure-aware Section-Aware BERT approach that segments and encodes key paragraphs (titles, responsibilities, requirements) for integrated modeling, building upon rule-based systems and classical baselines TF-IDF. Simultaneously, we evaluate large language models under both few-shot and fine-tuning settings on the same dataset to compare the capability boundaries of different modeling paradigms. Experimental results demonstrate that explicitly leveraging text structure significantly improves experience level prediction performance, particularly in scenarios with ambiguous job titles. Further error analysis reveals systemic challenges in this task, including confusion between Entry and Senior levels and the blurred boundaries of Mid-level positions. This research provides an effective modeling approach and analytical framework for understanding structured recruitment texts.