Scholarlink

The rapid growth of the IT industry is driven by emerging technologies such as Artificial Intelligence, Cloud Computing, Big Data Analytics, and the Internet of Things. Current job-matching platforms, such as LinkedIn and Indeed, often struggle to extract hidden or unmentioned skills from job descriptions, reducing the efficiency of job matching. This paper proposes a method that combines Co-occurrence Graphs and Natural Language Processing (NLP) techniques to improve job-skill matching. By analyzing relationships between frequently co-occurring skills in job descriptions and utilizing SpaCy’s Entity Ruler for skill extraction, the method enhances its ability to match candidate profiles with job postings. Evaluation metrics, including Precision at K (P@K), Mean Reciprocal Rank (MRR), and Normalized Discounted Cumulative Gain (NDCG), demonstrate the effectiveness of this approach. The results indicate the potential of the proposed method to provide more accurate and relevant job-skill matching.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Leveraging Co-Occurrence Graphs and NLP for Enhanced Job-Skill Matching

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Peera Sittiros,
  • Nirach Romyen,
  • Tanatorn Tanantong,
  • Krittakom Srijiranon

摘要

The rapid growth of the IT industry is driven by emerging technologies such as Artificial Intelligence, Cloud Computing, Big Data Analytics, and the Internet of Things. Current job-matching platforms, such as LinkedIn and Indeed, often struggle to extract hidden or unmentioned skills from job descriptions, reducing the efficiency of job matching. This paper proposes a method that combines Co-occurrence Graphs and Natural Language Processing (NLP) techniques to improve job-skill matching. By analyzing relationships between frequently co-occurring skills in job descriptions and utilizing SpaCy’s Entity Ruler for skill extraction, the method enhances its ability to match candidate profiles with job postings. Evaluation metrics, including Precision at K (P@K), Mean Reciprocal Rank (MRR), and Normalized Discounted Cumulative Gain (NDCG), demonstrate the effectiveness of this approach. The results indicate the potential of the proposed method to provide more accurate and relevant job-skill matching.