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

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 effectiveness of the proposed method. We foresee that our approach would transform the way of future human resources management.

I. Introduction

It is critical to recruit appropriate talents for certain positions in either companies or organizations. A company, especially the big ones such as “Google”, often receives hundreds of thousands of resumes for job application every year. Besides, headhunting or human resource (HR) managers may search for talents on job service platform, such as “LinkedIn” and “Monster”, to find appropriate candidates for certain job positions. The searched resulting list of resumes may be very long. Manually screening all the resumes to select possible candidates for further consideration, such as interview, is labor-intensive and time-consuming. From the talent perspective, he/she may want to know whether his/her resume is good enough. Therefore, it is desirable to develop some tool to assess the quality of each resume automatically.