JobViz: Skill-driven Visual Exploration of Job Advertisements

TL;DR

JobViz tackles the difficulty of matching job seekers to postings in massive online advertisements by centering analysis on skill requirements. It combines NLP-based skill extraction, a hierarchical skill framework, and three coordinated visual views (skill-job overview, post exploration with augmented radar-chart, and post detail) to enable multi-level exploration and comparison of job posts. The authors demonstrate the approach on CS/engineering postings from 51Job, validating the usefulness through two case studies and 26 user interviews. The results show that skill-centric visualization supports rapid filtering, pattern discovery across posts, and confident decision making, with potential to extend to other industries and languages.

Abstract

Online job advertisements on various job portals or websites have become the most popular way for people to find potential career opportunities nowadays. However, the majority of these job sites are limited to offering fundamental filters such as job titles, keywords, and compensation ranges. This often poses a challenge for job seekers in efficiently identifying relevant job advertisements that align with their unique skill sets amidst a vast sea of listings. Thus, we propose well-coordinated visualizations to provide job seekers with three levels of details of job information: a skill-job overview visualizes skill sets, employment posts as well as relationships between them with a hierarchical visualization design; a post exploration view leverages an augmented radar-chart glyph to represent job posts and further facilitates users' swift comprehension of the pertinent skills necessitated by respective positions; a post detail view lists the specifics of selected job posts for profound analysis and comparison. By using a real-world recruitment advertisement dataset collected from 51Job, one of the largest job websites in China, we conducted two case studies and user interviews to evaluate JobViz. The results demonstrated the usefulness and effectiveness of our approach.

Figures (11)

• Figure 1: The technical framework for skill extraction.
• Figure 2: JobViz, a skill-driven visual analytics system to help job seekers to efficiently explore the required skills and other relevant information of a large number of job posts in an interactive way. A) a skill-job overview of job postings is displayed for filtering job postings rapidly, which visualizes skill sets, employment posts as well as relationships between them; B) a post exploration view leverages a metaphor-based glyph to represent each job post and further enable users to gain a quick understanding of their key properties; C) a post detail view lists the details of selected job posts for further analysis and comparison.
• Figure 3: The system architecture of JobViz contains three modules: a storage module, a processing module, and a visualization module.
• Figure 4: An illustration of our augmented radar-chart glyph to show individual job posts in a compact manner, where the glyph integrates the horizon chart design. Sub-figure1 indicates a sector of a radar chart with spokes representing specific skills; Sub-figure2 indicates a horizon chart containing job posts distribution within; Sub-figure3 indicates a combination of them.
• Figure 5: A new glyph design augmented from radar-chart and horizon chart is proposed to represent each job post cluster in terms of both skill structures and post distributions in a compact manner.