How humorous is AI? Exploring ChatGPT's role in humor generation and human-AI interaction
Bibliographic record
Abstract
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.019 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".