Is Chat Gpt Biased Against Conservatives? An Empirical Study
Open accessThe DOI matches its Crossref record.
Abstract
This paper used Chat GPT to create Irish Limericks. During the creation process, a pattern was observed that seemed to create positive Limericks for liberal politicians and negative Limericks for conservative politicians. Upon identifying this pattern, the sample size was expanded to 80 and some mathematical calculations were made to determine whether the actual results were different from what probability theory would suggest. It was found that, at least in some cases, the AI was biased to favor liberal politicians and disfavor conservatives.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“22% use Chat GPT to generate paper outlines”
From Reflection on whether Chat GPT should be banned by academia from the perspective of education and teaching (2023) · cites this paper as McGee, 2023
In the citing paper
“48% of students use Chat GPT during exams”
From Reflection on whether Chat GPT should be banned by academia from the perspective of education and teaching (2023) · cites this paper as McGee, 2023
In the citing paper
“A recent survey revealed that nearly 89% of American college students use Chat GPT to complete homework tasks”
From Reflection on whether Chat GPT should be banned by academia from the perspective of education and teaching (2023) · cites this paper as McGee, 2023
In the citing paper
“with 53% using the tool for writing papers”
From Reflection on whether Chat GPT should be banned by academia from the perspective of education and teaching (2023) · cites this paper as McGee, 2023
Citations
Cites
Still being checked.
Cited by
Ray, P. P. (2023) · Internet of Things and Cyber-Physical Systems · doi:10.1016/j.iotcps.2023.04.003 · Cited by 2,463
Grassini, S. (2023) · Education Sciences · doi:10.3390/educsci13070692 · Cited by 1,048
“It has also been found that, in some cases, the information delivered by ChatGPT may be biased politically [57,58]; as well on religion, race, gender, and fairness (for a review see [59]).”
BackgroundYu, H. (2023) · Frontiers in Psychology · doi:10.3389/fpsyg.2023.1181712 · Cited by 409
“Additionally, 48% of students use Chat GPT during exams and 22% use Chat GPT to generate paper outlines (McGee, 2023).”
MethodShould ChatGPT be biased? Challenges and risks of bias in large language models
Ferrara, E. (2023) · First Monday · doi:10.5210/fm.v28i11.13346 · Cited by 282
Exploring the impact of ChatGPT: conversational AI in education
Bettayeb, A. M., Abu Talib, M., Sobhe Altayasinah, A. Z., & Dakalbab, F. (2024) · Frontiers in Education · doi:10.3389/feduc.2024.1379796 · Cited by 127
Metadata
- Authors
- McGee, R. W.
- Affiliations
- Fayetteville State University (US)
- Corresponding author
- McGee, Robert W.
- ORCID
- McGee, Robert W.
- Venue
- SSRN Electronic Journal
- Publisher
- Elsevier BV
- Published
- 2023
- ISSN
- 1556-5068 (ISSN-L)
- OpenAlex
- W6903901224
- Cited by
- 141
- References
- 0
- Citations by year
- 2026: 13 · 2025: 25 · 2024: 68 · 2023: 35
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Locations
- SSRN Electronic Journal (acceptedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Keywords
- ChatGPT, algorithmic bias, political ideology, conservatives, generative AI, political polarization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.