A Framework for Personality Prediction for E-Recruitment Using Machine Learning Algorithms

Abstract

With rapid advancements in technology, the process of recruitment has evolved from traditional methods to online and automated methods known as e-recruitment. While e-recruitment streamlines the initial screening process, assessing the personality and suitability of candidates continues to remain a challenge. In this paper, we propose a framework for online personality prediction to aid the e-recruitment process. The framework utilizes machine learning algorithms to analyze user data from multiple online sources like resumes, social media profiles, and responses to psychometric tests, and predict their personality type based on established psychological theories. Four popular personality prediction models - Big Five, Myers Briggs, HEXACO, and Enneagram are discussed. State-of-the-art natural language processing and deep learning techniques like BERT are explored for feature extraction from text data. Popular supervised machine learning algorithms like logistic regression, Naive Bayes, k-nearest neighbors, support vector machines, random forest, XGBoost, and LSTM are compared to build predictive models. The proposed framework can help recruiters shortlist candidates better matched to job requirements, leading to increased hiring satisfaction and productivity.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 14 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.