Sentiment over Scores: Text-based ESG analytics for sustainable investment decisions

Webster, Ellenora

Sentiment over Scores: Text-based ESG analytics for sustainable investment decisions

Webster, Ellenora

Permalink

Publication Type:: Thesis
Issue Date:: 2025

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (6.5 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Webster, Ellenora
dc.date.accessioned	2026-04-16T07:31:17Z
dc.date.available	2026-04-16T07:31:17Z
dc.date.issued	2025
dc.identifier.uri	http://hdl.handle.net/10453/194729
dc.description	University of Technology Sydney. Faculty of Business.	en_US.UTF-8
dc.description.abstract	After years of rapid growth, interest in environmental, social, and governance (ESG) investing is waning amid concerns that traditional ESG metrics are backward-looking, opaque, and inconsistent. This dissertation examines how forward-looking, data-driven ESG sentiment can overcome these limitations and enhance understanding of risk and return in financial markets as it relates to ESG. Chapter 2 outlines the shortcomings of traditional ESG ratings and introduces the ESG sentiment dataset, revealing unexpected characteristics compared with conventional sentiment measures. Chapter 3 investigates the link between ESG uncertainty and stock price volatility, showing that while ESG sentiment indicators can effectively predict volatility, their predictive power varies across measures. Chapter 4 addresses the “equity greenium” puzzle and introduces Breaking Buzz!, a novel metric that aligns sentiment with ESG ratings and demonstrates how delays in ESG classification can distort the greenium. Overall, this research provides practical tools for investors and policymakers, highlighting the potential of dynamic ESG sentiment to transform risk modelling, asset pricing, and sustainable investing in an evolving financial landscape.	en_US.UTF-8
dc.format	Thesis (PhD)
dc.language.iso	en	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/194729/1/thesis.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	© 2025 Ellenora Webster
dc.rights	au.edu.uts.lib/cph
dc.title	Sentiment over Scores: Text-based ESG analytics for sustainable investment decisions	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

After years of rapid growth, interest in environmental, social, and governance (ESG) investing is waning amid concerns that traditional ESG metrics are backward-looking, opaque, and inconsistent. This dissertation examines how forward-looking, data-driven ESG sentiment can overcome these limitations and enhance understanding of risk and return in financial markets as it relates to ESG. Chapter 2 outlines the shortcomings of traditional ESG ratings and introduces the ESG sentiment dataset, revealing unexpected characteristics compared with conventional sentiment measures. Chapter 3 investigates the link between ESG uncertainty and stock price volatility, showing that while ESG sentiment indicators can effectively predict volatility, their predictive power varies across measures. Chapter 4 addresses the “equity greenium” puzzle and introduces Breaking Buzz!, a novel metric that aligns sentiment with ESG ratings and demonstrates how delays in ESG classification can distort the greenium. Overall, this research provides practical tools for investors and policymakers, highlighting the potential of dynamic ESG sentiment to transform risk modelling, asset pricing, and sustainable investing in an evolving financial landscape.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/194729