Think You're Funny? ChatGPT might be Funnier

A study comparing jokes by people versus those told by ChatGPT shows that humans need to work on their material.

The research team behind the study published on Wednesday, July 3, in the journal PLOS ONE, took on the serious task of comparing participants’ reactions to jokes written by ChatGPT 3.5 and others written by people.

This was conducted in an effort to determine if artificial intelligence can outwit humans for a laugh, said Drew Gorenz, a doctoral candidate in social psychology at the USC Dornsife College of Letters, Arts and Sciences.

"Since ChatGPT can’t feel emotions itself but it tells novel jokes better than the average human, these studies provide evidence that you don’t need to feel the emotions of appreciating a good joke to tell a really good one yourself," Gorenz said.

One study compared the funniness of novel jokes crafted by regular people with the funniness of novel jokes generated by ChatGPT. Participants did so without knowing their author.

The researchers found that overall, nearly 70% of the participants rated the ChatGPT-generated jokes as funnier than those crafted by humans. A little over 25% of participants rated the human-crafted responses as funnier, and only about 5% rated jokes from both sources as equally funny. The results were consistent even when the researchers checked for differences across various demographics.

To see how ChatGPT might fare against professional humor writers, the researchers conducted a second study in which they challenged ChatGPT to develop new headlines in the satirical style of The Onion. They then asked another group of 200 participants to rate the funniness of original Onion headlines and of the new ChatGPT-generated headlines. Participants found ChatGPT’s headlines just as funny as the original Onion headlines.

How does one get people and AI to generate original jokes? For the first study, both ChatGPT and 105 participants completed three tasks, each including three prompts. In the first task, they crafted humorous new phrases for common acronyms. In a second task, both ChatGPT and the human writers generated funny answers to fill-in-the-blank phrases such as, "A lesser known room in the White House: ____." They were also prompted to come up with a "roast joke," a funny slam inspired by an awkward fictional scenario such as this:

"Imagine that one of your friends wants your opinion on how well she sings. She sings a minute or two to demonstrate her voice, and you cringe - she might be the worst singer you ever heard. When she asks, 'So how was it?' you decide to be honest so you say, 'To be honest, listening to that was like: _____'"

These three tasks resulted in more than 945 jokes written by 105 writers. ChatGPT was asked to generate 20 humorous answers for each prompt for a total of 180 jokes. A new group of participants then rated the funniness of the jokes.

In the second study, ChatGPT was fed original headlines from The Onion and asked to generate new headlines in the same style. A group of 200 participants was asked to rate the funniness of the original Onion headlines and the ChatGPT-generated ones without knowing the authorship.

Gorenz said his idea for the study stemmed in part from the entertainment world’s debate over writers’ concerns about the use of large language models (LLMs) like ChatGPT in entertainment production. The issue has been magnified due to recent strikes by Hollywood writers and actors who are fearful that the adoption of LLMs poses an existential threat to their respective professions, to art and to human creativity.

Gorenz, himself an amateur stand-up comedian, acknowledged a lifelong love for comedy that inspired his research with co-author, Norbert Schwarz, who is a co-director of the USC Dornsife Mind and Society Center and an expert on consumer judgment with the USC Marshall School of Business.

Gorenz said their study raises questions about the use of ChatGPT and other LLMs within the entertainment industry.

"The implications are more positive for people who merely want to reap the benefits of elevating their everyday communications with a dose of humor," he and Schwarz, a Provost Professor of Psychology and Marketing, wrote.

"But for professional comedy writers, our results suggest that LLMs can pose a serious employment threat," Schwarz added.

Whether AI gets the last laugh remains to be seen.

Gorenz D, Schwarz N.
How funny is ChatGPT? A comparison of human- and A.I.-produced jokes.
PLoS One. 2024 Jul 3;19(7):e0305364. doi: 10.1371/journal.pone.0305364

Most Popular Now

500 Patient Images per Second Shared thr…

The image exchange portal, widely known in the NHS as the IEP, is now being used to share as many as 500 images each second - including x-rays, CT, MRI...

Jane Stephenson Joins SPARK TSL as Chief…

Jane Stephenson has joined SPARK TSL as chief executive as the company looks to establish the benefits of SPARK Fusion with trusts looking for deployable solutions to improve productivity. Stephenson joins...

Is Your Marketing Effective for an NHS C…

How can you make sure you get the right message across to an NHS chief information officer, or chief nursing information officer? Replay this webinar with Professor Natasha Phillips, former...

We could Soon Use AI to Detect Brain Tum…

A new paper in Biology Methods and Protocols, published by Oxford University Press, shows that scientists can train artificial intelligence (AI) models to distinguish brain tumors from healthy tissue. AI...

Welcome Evo, Generative AI for the Genom…

Brian Hie runs the Laboratory of Evolutionary Design at Stanford, where he works at the crossroads of artificial intelligence and biology. Not long ago, Hie pondered a provocative question: If...

Telehealth Significantly Boosts Treatmen…

New research reveals a dramatic improvement in diagnosing and curing people living with hepatitis C in rural communities using both telemedicine and support from peers with lived experience in drug...

AI can Predict Study Results Better than…

Large language models, a type of AI that analyses text, can predict the results of proposed neuroscience studies more accurately than human experts, finds a new study led by UCL...

Using AI to Treat Infections more Accura…

New research from the Centres for Antimicrobial Optimisation Network (CAMO-Net) at the University of Liverpool has shown that using artificial intelligence (AI) can improve how we treat urinary tract infections...

Research Study Shows the Cost-Effectiven…

Earlier research showed that primary care clinicians using AI-ECG tools identified more unknown cases of a weak heart pump, also called low ejection fraction, than without AI. New study findings...

New Guidance for Ensuring AI Safety in C…

As artificial intelligence (AI) becomes more prevalent in health care, organizations and clinicians must take steps to ensure its safe implementation and use in real-world clinical settings, according to an...

Remote Telemedicine Tool Found Highly Ac…

Collecting images of suspicious-looking skin growths and sending them off-site for specialists to analyze is as accurate in identifying skin cancers as having a dermatologist examine them in person, a...

Philips Aims to Advance Cardiac MRI Tech…

Royal Philips (NYSE: PHG, AEX: PHIA) and Mayo Clinic announced a research collaboration aimed at advancing MRI for cardiac applications. Through this investigation, Philips and Mayo Clinic will look to...