• Graduate Program
    • Why study Business Data Science?
    • Research Master
    • Admissions
    • Course Registration
    • Facilities
  • Summer School
  • Research
  • News
  • Events
    • Events Calendar
    • Events archive
    • Tinbergen Institute Lectures
    • Summer School
      • Deep Learning
      • Economics of Blockchain and Digital Currencies
      • Foundations of Machine Learning with Applications in Python
      • Machine Learning for Business
      • Tuition Fees and Payment
      • Tinbergen Institute Summer School Program
    • Annual Tinbergen Institute Conference archive
  • Alumni
  • Magazine
Home | Events Archive | From BERT Topic Analysis to Regression Analysis: A Study on the Relationship Between ESG Themes and Corporate Characteristics in North American and European Companies
Research Master Pre-Defense

From BERT Topic Analysis to Regression Analysis: A Study on the Relationship Between ESG Themes and Corporate Characteristics in North American and European Companies

  • Series
    Research Master Defense
  • Speaker
    Su Yuanyuan
  • Date

    July 10, 2024

This study analyzes speeches by North American and European companies between 2001 and 2022 using the BERT methodology. The study includes modeling the themes of these speeches, exploring the relationship between the identified and ESG themes, and examining the evolution of these themes and their causes. Corporate attention to ESG themes was constructed from the content of ESG themes in corporate speeches. The researcher then examined the relationship between firms' ESG theme focus scores and firm characteristics (financial performance, market performance, risk, and analyst coverage).