Editorial: Analysis of Sentiment Estimates and Cognitive Fallacies in Large Language Models
- 14 July 2025
- journal article
- Published by Wiley in Intelligent Systems in Accounting, Finance and Management
- Vol. 32 (3)
Abstract
This paper describes some experimentation with the evolving ability of large language models to generate sentiment estimates. We find that current models seem to equal or even exceed the ability of human annotators in a case study of single sentiment sentences. In addition, using the large language models, we were able to identify a small number of sentences in the data set, where it appears that the annotator made errors in assessing the sentiment. Unfortunately, analysis of the LLM results also illustrates apparent cognitive biases in the LLM behavior. Those effects appear to include an “ostrich effect” and a “no one is good enough” effect cognitive bias in LLM sentiment estimates.Keywords
This publication has 16 references indexed in Scilit:
- Text Analysis of Evolving Emotions and Sentiments in COVID-19 Twitter CommunicationCognitive Computation, 2022
- A survey on sentiment analysis methods, applications, and challengesArtificial Intelligence Review, 2022
- GOOGLE'S Duplex: Pretending to be human*Intelligent Systems in Accounting, Finance and Management, 2019
- On the relationship between number of votes and sentiment in crowdsourcing ideas and comments for innovation: A case study of Canada's digital compassDecision Support Systems, 2016
- Do Sentiments Matter in Fraud Detection? Estimating Semantic Orientation of Annual ReportsIntelligent Systems in Accounting, Finance and Management, 2016
- Twitter Mining for Discovery, Prediction and Causality: Applications and MethodologiesIntelligent Systems in Accounting, Finance and Management, 2015
- Supporting decisions in real-time enterprises: autonomic supply chain systemsInformation Systems and e-Business Management, 2008
- Auditor environmental assessmentsInternational Journal of Accounting Information Systems, 2003
- Bounded rationality in social science: Today and tomorrowMind & Society, 2000
- On the Failure to Eliminate Hypotheses in a Conceptual TaskQuarterly Journal of Experimental Psychology, 1960