• Graduate Program
    • Why study Business Data Science?
    • Program Outline
    • Courses
    • Course Registration
    • Admissions
    • Facilities
  • Research
  • News
  • Summer School
    • Deep Learning
    • Machine Learning for Business
    • Tinbergen Institute Summer School Program
    • Receive updates
  • Events
    • Events Calendar
    • Events archive
    • Summer school
      • Deep Learning
      • Machine Learning for Business
      • Tinbergen Institute Summer School Program
      • Receive updates
    • Tinbergen Institute Lectures
    • Annual Tinbergen Institute Conference archive
  • Alumni
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).