ResumeNet: A Learning-based Framework for Automatic Resume Quality Assessment

TL;DR

This paper introduces ResumeNet, a neural-network framework for automatic resume quality assessment, utilizing a newly created dataset and innovative learning techniques to improve accuracy and efficiency in candidate screening.

Contribution

The paper develops a novel neural-network-based approach for RQA, introduces a new dataset of 10K resumes, and proposes semi-supervised and pair/triplet loss variants to handle label scarcity.

Findings

The proposed models outperform existing methods and website scoring in accuracy.

Semi-supervised and pair/triplet loss variants improve model robustness.

The approach has potential to revolutionize human resources management.

Abstract

Recruitment of appropriate people for certain positions is critical for any companies or organizations. Manually screening to select appropriate candidates from large amounts of resumes can be exhausted and time-consuming. However, there is no public tool that can be directly used for automatic resume quality assessment (RQA). This motivates us to develop a method for automatic RQA. Since there is also no public dataset for model training and evaluation, we build a dataset for RQA by collecting around 10K resumes, which are provided by a private resume management company. By investigating the dataset, we identify some factors or features that could be useful to discriminate good resumes from bad ones, e.g., the consistency between different parts of a resume. Then a neural-network model is designed to predict the quality of each resume, where some text processing techniques are incorporated. To deal with the label deficiency issue in the dataset, we propose several variants of the model by either utilizing the pair/triplet-based loss, or introducing some semi-supervised learning technique to make use of the abundant unlabeled data. Both the presented baseline model and its variants are general and easy to implement. Various popular criteria including the receiver operating characteristic (ROC) curve, F-measure and ranking-based average precision (AP) are adopted for model evaluation. We compare the different variants with our baseline model. Since there is no public algorithm for RQA, we further compare our results with those obtained from a website that can score a resume. Experimental results in terms of different criteria demonstrate the effectiveness of the proposed method. We foresee that our approach would transform the way of future human resources management.