Machine Learning and AI Used to Detect Gender Bias in Job Advertisements

Strategic Insights -

Researchers from Comillas Pontifical University have developed a system using machine learning and natural language processing (NLP) to detect gender bias in job advertisements. The system, which combines NLP with Term Frequency-Inverse Document Frequency (TF-IDF) and Latent Dirichlet Allocation (LDA), analyzes the language used in job postings to identify words and phrases that may be biased towards one gender. According to the study, the system was tested on a database of 2000 job ads in four different sectors and found evidence of gender-biased practices.

Key Takeaways:

  • The system uses machine learning and NLP to detect gender bias in job advertisements, focusing on the application of NLP to identify words and phrases that may be biased towards one gender.
  • The research aims to provide equal access to employment opportunities from the initial stage of the recruitment process, highlighting the importance of addressing gender bias in job postings.
  • Clustering techniques were applied to create groups based on the target public and the type of language used, providing evidence of gender-biased practices.
  • The system was tested using a database of 2000 job ads in four different sectors: nursery, secretarial, managerial, and engineering.
  • The research has been peer-reviewed and published in the International Journal of Pattern Recognition and Artificial Intelligence.
  • The study's authors, Rafael Palacios, Cristina Puente, Ivan Sanchez-Perez, Evhenia Kolomiyets-Ludwig, Clara Palacios-Castrillo, and Patrick S. P. Wang, are from Comillas Pontifical University.

Statistics:

  • 2000 job ads were used to test the system in four different sectors: nursery, secretarial, managerial, and engineering.
  • The system combined NLP with TF-IDF and LDA to analyze the language used in job postings.
  • Using clustering techniques, the research identified groups based on the target public and type of language used.
  • The study found evidence of gender-biased practices in job postings, highlighting the need for equal access to employment opportunities.

Sources:

  • "Analysis of Job Offers To Measure Gender Barriers Through Natural Language Processing and Soft Computing Techniques." International Journal of Pattern Recognition and Artificial Intelligence, 2025;39(05).
  • World Scientific Publishing - www.worldscientific.com/; International Journal of Pattern Recognition and Artificial Intelligence - www.worldscinet.com/ijprai/ijprai.shtml.
  • Rafael Palacios, Cristina Puente, Ivan Sanchez-Perez, Evhenia Kolomiyets-Ludwig, Clara Palacios-Castrillo, and Patrick S. P. Wang. "Study Data from Comillas Pontifical University Update Understanding of Pattern Recognition and Artificial Intelligence (Analysis of Job Offers To Measure Gender Barriers Through Natural Language Processing and Soft Computing Techniques)." Journal of Engineering. May 26, 2025; p 3054.