MétaCan
Menu
Back to cohort
Record W4414517301 · doi:10.1016/j.chbr.2025.100807

How humorous is AI? Exploring ChatGPT's role in humor generation and human-AI interaction

2025· article· en· W4414517301 on OpenAlexafffund
Yi Cao, Jiahao Cao, Yubo Hou, Li‐Jun Ji

Bibliographic record

VenueComputers in Human Behavior Reports · 2025
Typearticle
Languageen
FieldPsychology
TopicHumor Studies and Applications
Canadian institutionsQueen's University
FundersPeking UniversityChina Postdoctoral Science FoundationSocial Sciences and Humanities Research Council of CanadaNational Natural Science Foundation of China
KeywordsHumor researchInterpersonal communicationCoping (psychology)CognitionInterpersonal relationshipInterpersonal interactionSocial relation

Abstract

fetched live from OpenAlex

The rapid evolution of artificial intelligence has raised important questions about its ability to replicate nuanced human cognitive functions -- particularly humor generation. This research investigates GPT-4o, an advanced language model, focusing on its capacity to generate humor, how it compares to human-generated humor, and its potential applications in human-AI interaction. The main variables include humor generation, coping, strategy, and interpersonal conflict. We hypothesize that GPT-4o outperforms humans in humor generation and can help individuals manage interpersonal conflicts by effectively using humor, based on a theoretical framework that integrates humor theory and human-AI interaction models. Drawing on data from a racially diverse sample from the U.S. the research employs experimental methods across four studies. Study 1 compares GPT-4o and human humor generation using textual and visual prompts. Study 2 examines how social context (positive vs. negative) influences humor coping strategies in both AI and human responses. Study 3 identifies the most effective humor types in negative social contexts. Study 4 explores GPT-4o's role in managing interpersonal conflict through humor in human-AI interaction. Findings reveal that GPT-4o excels in generating sentence-based humor, particularly in response to negative social contexts, and outperforms humans in humor coping strategies. In response to negative contexts, both humans and GPT-4o identify self-enhancing humor as the most effective strategy. Furthermore, GPT-4o demonstrates effectiveness in conflict resolution, as evidenced by positive feedback from both humor senders and recipients. These results offer theoretical and practical insights into AI's emerging role in emotional support, stress reduction, and socially sensitive communication. • GPT-4o outperforms humans in text-based humor but not image-based humor. • GPT-4o generates better humor than humans, especially in negative situations. • Self-enhancing humor is the most effective strategy for both GPT-4o and humans. • Senders and recipients rated GPT-4o's humor funniest, most effective and likable.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.019
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.002
Threshold uncertainty score0.013

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.019
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0010.002
Scholarly communication0.0020.002
Open science0.0000.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.078
GPT teacher head0.387
Teacher spread0.309 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations2
Published2025
Admission routes2
Has abstractyes

Explore more

Same venueComputers in Human Behavior ReportsSame topicHumor Studies and ApplicationsFrench-language works237,207