<ul data-eligibleForWebStory="true">Human capital (HC) is gaining importance in corporate value creation, but lacks defined measurement and disclosure rules.Researchers developed a comprehensive list of HC-related keywords classified into five subcategories using a machine learning algorithm.The subcategories include DEI, health and safety, labor relations and culture, compensation and benefits, and demographics and other.The lexicon, corporate HC disclosures, and Python code used in the study are shared.The data and code provided can be used by researchers to analyze corporate human capital disclosures.Examples of using the data and code, including fine-tuning a BERT model, are detailed in the research.The HC lexicon can be used by researchers to analyze corporate communications and address HC-related questions.Future research opportunities related to HC management and disclosure are discussed.The study aims to provide a tool for researchers to analyze the multidimensional aspects of HC management in corporations.