AI-Driven Optimization of Job Advertisements through Knowledge-Based Techniques and Semantic Matching | ||||
| Port-Said Engineering Research Journal | ||||
| Articles in Press, Accepted Manuscript, Available Online from 13 February 2024 | ||||
| Document Type: Short Notes | ||||
| DOI: 10.21608/pserj.2024.260755.1308 | ||||
 View on SCiNiTO | ||||
| Author | ||||
Shatha Hazim Ajaj 
| ||||
| Computer science, University of Bath, Bath, United Kingdom | ||||
| Abstract | ||||
| This research underscores the significance of job posting quality in attracting highly qualified candidates throughout the recruitment process. It highlights the necessity of refining job postings by incorporating standardized occupational details concerning job requirements and qualifications. This improvement enhances the overall recruitment process and substantially raises the likelihood of identifying suitable candidates. Regrettably, numerous job postings suffer from insufficient information, posing a challenge for job seekers in comprehending the intricacies of the job. To tackle this issue, the research endeavors to develop an AI-driven optimization assistant for job advertisements that aligns with the guidelines set by Google for job postings. Employing knowledge-based techniques and semantic matching, this assistant aims to provide precise information about occupations and tailor recommendations based on industry-specific requirements. By enhancing searchability, the assistant seeks to actively aid recruiters in optimizing job advertisements and improving the alignment between recruiters and candidates. Thus, this research aims to offer practical solutions for enhancing the effectiveness of job postings and streamlining the recruitment process. | ||||
| Keywords | ||||
| Recruitment; Optimization assistant; Semantic matching; Knowledge base; Natural Language Processing (NLP) | ||||
|
Statistics Article View: 66 |
||||
