Not logged in.
Quick Search - Contribution
Contribution Details
| Type | Journal Article |
| Scope | Discipline-based scholarship |
| Title | Sentiment spin: Attacking financial sentiment with GPT-3 |
| Organization Unit | |
| Authors |
|
| Item Subtype | Original Work |
| Refereed | Yes |
| Status | Published in final form |
| Language |
|
| Journal Title | Finance Research Letters |
| Publisher | Elsevier |
| Geographical Reach | international |
| ISSN | 1544-6123 |
| Volume | 55 |
| Number | B |
| Page Range | 103957 |
| Date | 2023 |
| Abstract Text | In this study, we explore the susceptibility of financial sentiment analysis to adversarial attacks that manipulate financial texts. With the rise of AI readership in the financial sector, companies are adapting their language and disclosures to fit AI processing better, leading to concerns about the potential for manipulation. In the finance literature, keyword-based methods, such as dictionaries, are still widely used for financial sentiment analysis due to their perceived transparency. However, our research demonstrates the vulnerability of keyword-based approaches by successfully generating adversarial attacks using the sophisticated transformer model, GPT-3. With a success rate of nearly 99% for negative sentences in the Financial Phrase Bank, a widely used database for financial sentiment analysis, we highlight the importance of incorporating robust methods, such as context-aware approaches such as BERT, in financial sentiment analysis. |
| Free access at | Official URL |
| Related URLs | |
| Digital Object Identifier | 10.1016/j.frl.2023.103957 |
| Other Identification Number | merlin-id:23687 |
| PDF File |
Download from ZORA
|
| Export |
BibTeX
EP3 XML (ZORA)
|
| Keywords | sentiment analysis in financial markets, Keyword-based approach, FinBERT, GPT-3 |
| Additional Information | Bereits als Working Paper in Swiss Finance Institute Research Paper erschienen: https://dx.doi.org/10.2139/ssrn.4337182. |