Financial Sentiment Analysis on News and Reports Using Large Language Models and FinBERT

Financial sentiment analysis (FSA) is crucial for evaluating market sentiment and making well-informed financial decisions. The advent of large language models (LLMs) such as BERT and its financial variant, FinBERT, has notably enhanced sentiment analysis capabilities. This paper investigates the ap...

Full description

Saved in:
Bibliographic Details
Published inIEEE International Conference on Power, Intelligent Computing and Systems (Online) pp. 717 - 721
Main Authors Shen, Yanxin, Zhang, Pulin Kirin
Format Conference Proceeding
LanguageEnglish
Published IEEE 26.07.2024
Subjects
Online AccessGet full text
ISSN2834-8567
DOI10.1109/ICPICS62053.2024.10796670

Cover

Abstract Financial sentiment analysis (FSA) is crucial for evaluating market sentiment and making well-informed financial decisions. The advent of large language models (LLMs) such as BERT and its financial variant, FinBERT, has notably enhanced sentiment analysis capabilities. This paper investigates the application of LLMs and FinBERT for FSA, comparing their performance on news articles, financial reports and company announcements. The study emphasizes the advantages of prompt engineering with zero-shot and few-shot strategy to improve sentiment classification accuracy. Experimental results indicate that GPT -40, with few-shot examples of financial texts, can be as competent as a well fine-tuned FinBERT in this specialized field.
AbstractList Financial sentiment analysis (FSA) is crucial for evaluating market sentiment and making well-informed financial decisions. The advent of large language models (LLMs) such as BERT and its financial variant, FinBERT, has notably enhanced sentiment analysis capabilities. This paper investigates the application of LLMs and FinBERT for FSA, comparing their performance on news articles, financial reports and company announcements. The study emphasizes the advantages of prompt engineering with zero-shot and few-shot strategy to improve sentiment classification accuracy. Experimental results indicate that GPT -40, with few-shot examples of financial texts, can be as competent as a well fine-tuned FinBERT in this specialized field.
Author Shen, Yanxin
Zhang, Pulin Kirin
Author_xml – sequence: 1
  givenname: Yanxin
  surname: Shen
  fullname: Shen, Yanxin
  email: ssyysyx@zju.edu.cn
  organization: Zhejiang University,Hangzhou,Zhejiang,China
– sequence: 2
  givenname: Pulin Kirin
  surname: Zhang
  fullname: Zhang, Pulin Kirin
  email: kirinpzhang@gmail.com
  organization: Lehigh University,Bethlehem,Pennsylvania,USA
BookMark eNo1kM1OAjEUhavRRETewEV9gMHe3pn-LHECSjL-BDBxR-r0QmqGDpliDG_vJOjmO2dx8i3ONbuIbSTG7kCMAYS9n5dv83KppChwLIXMxyC0VUqLMzay2hosBOocoThnA2kwz0yh9BUbpfQlhEAJoI0ZsI9ZiC7WwTV8SfEQdj34JLrmmELibeQv9JO4i54vaN92h8TfU4hbXrluSz3j9tv15bn11Jx2vfBhuljdsMuNaxKN_nLIVrPpqnzKqtfHeTmpsmDhkKkChNFeWeuMduQAbWEdKjS1R6OE3FgA6aSvP3NbeAJCL4WyBDV63HgcstuTNhDRet-FneuO6_8v8Bd8x1T9
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICPICS62053.2024.10796670
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798350374315
EISSN 2834-8567
EndPage 721
ExternalDocumentID 10796670
Genre orig-research
GroupedDBID 6IE
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i91t-651087d699a87aea13959a3638cd38602f9112a2dcb495de1e3d2069e1c3d3fd3
IEDL.DBID RIE
IngestDate Wed Jan 01 06:01:57 EST 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i91t-651087d699a87aea13959a3638cd38602f9112a2dcb495de1e3d2069e1c3d3fd3
PageCount 5
ParticipantIDs ieee_primary_10796670
PublicationCentury 2000
PublicationDate 2024-July-26
PublicationDateYYYYMMDD 2024-07-26
PublicationDate_xml – month: 07
  year: 2024
  text: 2024-July-26
  day: 26
PublicationDecade 2020
PublicationTitle IEEE International Conference on Power, Intelligent Computing and Systems (Online)
PublicationTitleAbbrev ICPICS
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211788
Score 1.9192663
Snippet Financial sentiment analysis (FSA) is crucial for evaluating market sentiment and making well-informed financial decisions. The advent of large language models...
SourceID ieee
SourceType Publisher
StartPage 717
SubjectTerms Accuracy
Analytical models
BERT
Computational modeling
Context modeling
FinBERT
Fluctuations
Large language models
NLP
Prompt engineering
Real-time systems
Sentiment analysis
Zero shot learning
Title Financial Sentiment Analysis on News and Reports Using Large Language Models and FinBERT
URI https://ieeexplore.ieee.org/document/10796670
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3dS8MwEA-6B_FJxYnfRPC1tUm6fLw6NjbRMdyEvY00uYIonWj74l_vpV0nCoIvJZQmhKSXu9_l7neEXAthmdOSRXnOJQIUzaJMCR6BUJol4GxaE2k_TOToKb1b9BbrZPU6FwYA6uAziEOzvsv3K1cFVxlKuELrXCFC31bKNMlaG4eKQCiDeG6HXK15NG_G_em4P5Mc_zMEgjyN2_4_KqnUimS4RybtFJr4kZe4KrPYff5iZ_z3HPdJ9ztnj0432uiAbEFxSBbDllCDzkJYUOhLWx4SuipoOOOoLTxtDPEPWocQ0PsQH47PxpdJQ8G01-Y7HPB28DjvkvlwMO-PonUthejZsDKSKHpaeWmM1cqCRbuvZ6xA4XNehDJUOR563HLvMkRMHhgIzxNpgDnhRe7FEekUqwKOCU114hKdWsEVpCCksUblaBSBtkyBUSekG1Zl-dawZSzbBTn94_0Z2Q2bE_ylXJ6TTvlewQUq-jK7rDf4C3RWpak
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3dS8MwEA-ioD6pOPHbCL62tkmXj1fHxqbbGK7C3kaaXEGUTrR78a_30q4TBcGXUkp7hKSXu9_l7neE3HBuYqtEHOQ5EwhQVBxkkrMAuFRxBNYkFZH2aCz6T8n9rD1bFatXtTAAUCWfQehvq7N8t7BLHypDDZfonUtE6FttlCHrcq11SIUjmEFEt02uV0yat4POZNCZCoZ_GkJBloSNhB-9VCpT0tsj42YQdQbJS7gss9B-_uJn_Pco90nru2qPTtb26IBsQHFIZr2GUoNOfWKQ_5Y2TCR0UVC_y1FTOFq74h-0SiKgQ58hjtc6mkl9y7TX-j0UeNd9TFsk7XXTTj9YdVMInnVcBgKVT0kntDZKGjDo-bW14ah-1nHfiCrHbY8Z5myGmMlBDNyxSGiILXc8d_yIbBaLAo4JTVRkI5UYziQkwIU2WuboFoEysQQtT0jLz8r8rebLmDcTcvrH8yuy009Hw_lwMH44I7t-oXz0lIlzslm-L-ECzX6ZXVaL_QVbFKj6
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=IEEE+International+Conference+on+Power%2C+Intelligent+Computing+and+Systems+%28Online%29&rft.atitle=Financial+Sentiment+Analysis+on+News+and+Reports+Using+Large+Language+Models+and+FinBERT&rft.au=Shen%2C+Yanxin&rft.au=Zhang%2C+Pulin+Kirin&rft.date=2024-07-26&rft.pub=IEEE&rft.eissn=2834-8567&rft.spage=717&rft.epage=721&rft_id=info:doi/10.1109%2FICPICS62053.2024.10796670&rft.externalDocID=10796670