Humans vs. ChatGPT: Evaluating Annotation Methods for Financial Corpora

Jamshed Kaikaus, Haoen Li, Robert J. Brunner

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Given the vast amount of unstructured financial text data available today, there is a high demand for reliable, quality annotations to facilitate robust model development. However, traditional methods can often be expensive and time-inefficient. In this study, we investigate annotations for emotion, sentiment, and cognitive dissonance generated by the large language models (LLMs), GPT-3.5 and GPT-4, for quarterly earnings conference calls and compare them against human annotations obtained via traditional methods. We also investigate different prompt engineering choices on LLM annotation quality, experimenting with 4 styles of prompts centered around varying the amount of contextual information given and how it is presented to the models. Our results show the GPT models are not only more consistent and reliable than human annotators, but also provide annotations in a more cost- and time-efficient manner.

Original languageEnglish (US)
Title of host publicationProceedings - 2023 IEEE International Conference on Big Data, BigData 2023
EditorsJingrui He, Themis Palpanas, Xiaohua Hu, Alfredo Cuzzocrea, Dejing Dou, Dominik Slezak, Wei Wang, Aleksandra Gruca, Jerry Chun-Wei Lin, Rakesh Agrawal
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2831-2838
Number of pages8
ISBN (Electronic)9798350324457
DOIs
StatePublished - 2023
Event2023 IEEE International Conference on Big Data, BigData 2023 - Sorrento, Italy
Duration: Dec 15 2023Dec 18 2023

Publication series

NameProceedings - 2023 IEEE International Conference on Big Data, BigData 2023

Conference

Conference2023 IEEE International Conference on Big Data, BigData 2023
Country/TerritoryItaly
CitySorrento
Period12/15/2312/18/23

Keywords

  • earnings calls
  • emotion recognition
  • large language models
  • sentiment analysis

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'Humans vs. ChatGPT: Evaluating Annotation Methods for Financial Corpora'. Together they form a unique fingerprint.

Cite this