Unveiling tone manipulation in MD&A: Evidence from ChatGPT experiments

Piaopeng Song, Hanglin Lu and Yongjie Zhang

Finance Research Letters, 2024, vol. 67, issue PA

Abstract: This research uses ChatGPT-3.5 and ChatGPT-4 to investigate tone manipulation in the management discussion and analysis of annual reports of Chinese-listed companies. We find that the quantification of emotional content in text using financial BERT model and dictionary approach is inconsistent due to two kinds of manipulation: "Expression Manipulation" and "Word Manipulation". Based on ChatGPT we verify the manipulative behavior of complex expressions and sentiment word substitutions. Our research suggests that using ChatGPT with appropriate cue words can help alleviate tone manipulation in financial texts, with GPT-4 having a better effect.

Keywords: ChatGPT; Syntactic Complexity; Tone Manipulation; MD&A (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1544612324008675
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:finlet:v:67:y:2024:i:pa:s1544612324008675

DOI: 10.1016/j.frl.2024.105837

Access Statistics for this article

Finance Research Letters is currently edited by R. Gençay

More articles in Finance Research Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().