71. Actions Speak Louder than Words? Detecting Greenwashing via AI-Driven Sentiment Analysis of Management Narratives
Invited abstract in session Operations Research and the Common Good (special edition), stream OR and Ethics, and Societal Perspectives.
Authors (first author is the speaker)
| 1. | QIYAO HONG
|
| Department of Accounting, National Yunlin University of Science and Technology (TAIWAN) |
Abstract
This study proposes an AI framework using FinBERT to detect greenwashing in Taiwan's tech sector (2022-2024). We analyze sentiment in Chairman's messages versus actual ESG performance. We hypothesize that underperforming firms may use overly optimistic narratives to mask deficiencies. By quantifying this "decoupling," we investigate whether a negative correlation exists between tone and performance. The study aims to demonstrate how NLP tools serve as an early warning system for strategic obfuscation.
Keywords
- Sustainable Development
- Artificial Intelligence
- Ethics and Governance
Status: accepted
Back to the list of papers