Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/335550 
Year of Publication: 
2025
Publisher: 
ZBW - Leibniz Information Centre for Economics, Kiel, Hamburg
Abstract: 
This paper investigates the role of investor sentiment in the pricing and volatility dynamics of green bond exchange-traded funds (ETFs). For a construction of green sentiment one original and two already existing natural language processing models are used and evaluated. The VAR model found no significant impact of green sentiment on ETF returns. The GARCH (1,1) estimation strongly supported the presence of volatility clustering and time-varying volatility in green bond ETF returns, validating the use of conditional heteroskedasticity models. Regressing the conditional volatility on sentiment scores revealed a significant negative relationship – higher sentiment is associated with lower volatility. This finding implies that positive green sentiment contributes to market stability and may reduce perceived risk, reinforcing the importance of investor psychology in green financial markets.
Subjects: 
Machine learning
NLP model
ESG
Exchange Traded Funds
JEL: 
C45
C55
G11
G17
Document Type: 
Working Paper

Files in This Item:
File
Size
718.5 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.