Joking Chatbots Help Learning?

 Brought the below up before, here is more detail. Humor is powerful, but how do we harness it? Need a good way.  Thoughts?  See my Humor link.

Joke-Cracking Chatbots Boost Learning Levels

By Paul Marks, Commissioned by CACM Staff, July 20, 2021

Technology has brought us many wonderful things, but chatbots are not one of them. On banking and e-commerce sites, for instance, where these text-based conversational agents have been pressed into service to replace customer-support staff, even simple requests are often met with baffling arrays of options.

For example, a bank's online chatbot recently asked me which of four types of savings account I was interested in – but it did not explain how they differed from each other. When I typed in "I don't know" the bankbot replied tersely: "That is not an option". It then looped me back to those original options. No wonder some consumer commentators – like this one at Forbes – say such clumsy chatbot implementations are "killing customer service".

So, when I heard researchers in Canada had decided to add a sense of humor to chatbots, I feared the worst. Surely making light of giving people inadequate information would be adding insult to injury? Well, apparently not: the researchers have found that comedy-capable chatbots could have an important role, although in education – not customer support.

Speaking at the virtual Conference on Human Factors in Computing Systems (CHI2021) in May, human-computer interaction researchers led by Jessy Ceha and Ken Jen Lee of the University of Waterloo in Ontario, Canada, described how their team set out to investigate whether a particular way of studying a subject, called learning-by-teaching, might be enhanced by a witty chatbot.

In garden variety learning-by-teaching, typically three students research a subject using certain teacher-approved resources like books, Websites, diagrams, and photographs. They then prepare a lesson and teach that subject to another small group of students, the process of lesson-planning having helped them not only improve their own factual recall of the subject at hand, but also, in having to work out how to teach the subject, develop their problem-solving skills.

The Waterloo team wondered, what if the teaching group got to coach a smart chatbot instead of fellow students? Further, they wondered whether a chatbot with a sense of humor, in getting a few laughs out of its teachers, might better motivate them, lower their stress and anxiety levels, and help them learn more?  ... ' 

Virtual Humor Agents to Promote Learning

Always liked the idea of using humor to promote engagement.  Used it a bit in our brand equity agents.  Here is another, somewhat more sophisticated approach.   See also work by Andrew Tarvin, colleague, who does interesting things in  this space.  You can see more about his work in the tag below. See also his book https://www.humorthatworks.com/  and related consulting.

Do Humorous Teachable Virtual Agents Enhance Learning, Outcomes?

University of Waterloo Cheriton School of Computer Science (Canada),  May 11, 2021

A study by researchers at the University of Waterloo in Canada considered whether a teachable virtual agent could improve learning and outcomes by employing humor when interacting with students. Using the online learning-by-teaching platform Curiosity Notebook, the researchers evaluated the impact of affiliative and self-defeating humor styles on the effectiveness of such an agent, as well as humor of a self-enhancing nature, and a neutral style in which no verbal humor was expressed. Waterloo's Jessy Ceha said, "We found that participants who interacted with the agent with an affiliative humor style showed an increase in motivation during the teaching task and an increase in the amount of effort they put into teaching the agent. The participants who interacted with the agent with a self-defeating style also showed an increase in effort, but they didn't find it as enjoyable an experience."  ...'

Laugh More, Lead Better

Recall some of our own experiments in humor-augmented management.   

Laugh more, lead better  in McKinsey

Naomi Bagdonas and Connor Diemand-Yauman, lecturers at Stanford’s Graduate School of Business, hilariously explore the power at the intersection of humor, business, and leadership. It’s no joke. ...'

See Andrew Tarvin's book.

Using Emotion and Humor to Combat Science Misinformation

 Interesting thought here,  how do we do it effectively? 

Using Emotion and Humor to Combat Science Misinformation    By University of Utah

April 13, 2021  in CACM

Humor might help combat scientific misinformation published online and on social media, according to "Emotion and Humor as Misinformation Antidotes,"   by Sara K. Yeo and Meaghan McKasy, published in Proceedings of the National Academy of Sciences.

"Recent research sheds light on how funny science and emotions can help explain and potentially overcome our inability or lack of motivation to recognize and challenge misinformation," the authors say. "Understanding how emotion and humor shape the public's understanding of science is one more resource that can aid communicators' efforts to combat misinformation."

Yeo, of the University of Utah, and McKasy, of Utah Valley University, say humor is also linked to people's evaluations of an information source. Yeo's recent research shows that scientists who use humor are perceived as more likable yet retain their credibility as an expert.

From University of Utah

Robots and Humor

A long term thread, the value of humor to learn, instruct, collaborate.

Comedy Club Performances Provide Insights on How Robots, Humans Connect via Humor

Oregon State University News
Steve Lundeberg
May 18, 2020

Two studies by Oregon State University (OSU) researchers evaluated a robot comedian's performance at comedy clubs to gather data to enable more effective robot-human interplay through humor. Human comics helped develop material used by John the Robot in 22 performances in Los Angeles and 10 in Oregon. The Los Angeles study concluded that audiences found a robot comic with good timing to be much funnier than one without good timing. The Oregon study found that an "adaptive performance"—delivering post-joke "tags" that acknowledge an audience's response—was not necessarily funnier overall, but nearly always improved audience perception of individual jokes. OSU's Naomi Fitter said the research has implications for artificial intelligence projects to understand group responses to entertaining social robots in the real world.  ... " 

Robot Comedy for Data?

Ultimately we will have to be able do a better job of getting data based on reactions to proposals.  Is standup comedy using robots a model of how to get this kind of data? 

What's the Deal With Robot Comedy?
How to teach a robot to be a stand-up comedian
By Naomi Fitter in IEEE Spectrum

Nao robot learning to be a stand-up comedian

This is a guest post. The views expressed here are solely those of the author and do not represent positions of IEEE Spectrum or the IEEE.

In my mythical free time outside of professorhood, I’m a stand-up comedian and improviser. As a comedian, I’ve often found myself wishing I could banter with modern commercial AI assistants. They don’t have enough comedic skills for my taste! This longing for cheeky AI eventually led me to study autonomous robot comedians, and to teach my own robot how to perform stand-up.

I’ve been fascinated with the relationship between comedy and AI even before I started doing comedy on my own in 2013. When I moved to Los Angeles in 2017 as a postdoctoral scholar for the USC Interaction Lab, I began performing in roughly two booked comedy shows per week, and I found myself with too good of an opportunity for putting a robot onstage to pass up.

Programming a NAO robot for stand-up comedy is complicated. Some joke concepts came easily, but most were challenging to evoke. It can be tricky to write original comedy for a robot since robots have been part of television and cinema for quite some time. Despite this legacy, we wanted to come up with a perspective for the robot that was fresh and not derivative.

Another challenge was that in my human stand-up comedy, I write almost entirely from real-life experience, and I’ve never been a robot! I tried different thought exercises—imagining myself to be a robot with different annoyances, likes, dislikes, and “life” experiences. My improv comedy training with the Upright Citizens Brigade started to come in handy, as I could play-act being a robot, map classic (and even somewhat overdone) human jokes to fit robot experiences, and imagine things like, “What is a robot family?”, “What is a robot relationship like?”, and “What are drugs for a robot?” ... "

Predicting Humor for Engagement

Humor as engagement.     Can it be delivered artificially, as a strong component of story?

It's No Joke: AI Beats Humans at Making You Laugh    |by Dina Gerdeman  in HBSWK

We all enjoy sharing jokes with friends, hoping a witty one might elicit a smile—or maybe even a belly laugh. Here’s one for you:

A lawyer opened the door of his BMW, when, suddenly, a car came along and hit the door, ripping it off completely. When the police arrived at the scene, the lawyer was complaining bitterly about the damage to his precious BMW.

"Officer, look what they've done to my Beeeeemer!” he whined.

"You lawyers are so materialistic, you make me sick!” retorted the officer. "You're so worried about your stupid BMW that you didn't even notice your left arm was ripped off!”

“Oh, my god,” replied the lawyer, finally noticing the bloody left shoulder where his arm once was. “Where's my Rolex?!”

Do you think your friends would find that joke amusing—well, maybe those who aren’t lawyers?

A research team led by Harvard Business School post-doctoral fellow Michael H. Yeomans put this laughing matter to the test. In a new study, he used that joke and 32 others to determine whether people or artificial intelligence (AI) could do a better job of predicting which jokes other people consider funny. ... "

Humor that Works: and a new Book!

My former P&G Colleague Andrew Tarvin has been promoted to the prestigious group:

P&G Alumni Visionaries under 40
Announcing our “Visionaries Under 40” to be recognized at the 2019 Global Conference in Madrid this October.  .... 

Andrew Tarvin
Humor Engineer
Humor That Works    https://www.humorthatworks.com/ 

See his new book: Humor that Works:The Missing Skill for Success and Happiness at Work    

Andrew Tarvin is a speaker and trainer, and has delivered more than 600 programs to over 40,000 people at 250-plus organizations. He was the recipient of the 2019 President’s Award for Distinguished Service from the NSA NYC, and was one of the first thirty improv practitioners to be certified by the Applied Improvisation Network. His TEDx talk has more than 5 million views and his recent book, “The United States of Laughter”, won the 2019 Book Award from the Association for Applied and Therapeutic Humor.  ..." 

Humor That Works

Former Colleague Andrew Tarvin,  of Humor that Works,  is giving a webinar in January for the P&G Alumni network.    Thought I would give him a shout out .... check out his space.  We need more humor.

https://www.humorthatworks.com/

Andrew Tarvin is the world’s first Humor Engineer teaching people how to get better results while having more fun. He has worked with thousands of people at 250+ organizations, including P&G, GE, and Microsoft.

Today’s world is constantly driving towards greater efficiency. The only problem is that you can’t be efficient with humans because they have “emotions” and “feelings.” And those feelings get in the way of greater productivity. The key is to focus on effectiveness.

This webinar will teach you how to accomplish your goals and not just complete a task. Combining elements of leadership, emotional intelligence, and software engineering, attendees will walk away knowing how to work effectively with the most challenging resource there is: humans.

Presenter Bio:
Andrew Tarvin is the world’s first Humor Engineer teaching people how to get better results while having more fun. He has worked with thousands of people at 250+ organizations, including P&G, GE, and Microsoft.

Prior to starting his company, Humor That Works, Andrew was an IT project manager for Procter & Gamble and the self-proclaimed Corporate Humorist of the company. During his time at P&G, he worked for R&D and engineering in Cincinnati, for P&G Prestige in NYC, and wrote a terrible rap jingle for Pringles.

He is a best-selling author, has been featured in The Wall Street Journal, Forbes, and TEDx, and has delivered programs in 50 states, 20 countries, and 4 continents. He loves the color orange and is obsessed with chocolate. ..... 

Thanks,
P&G Alumni Network

Detecting Funny

The emergence of a New Yorker crowdsourcing system that tries to determine, with interaction and algorithm, what is funny.  In CNet.  Seems this could also be linked to Cyc and perhaps Lucid, to determine the subtlety of our knowledge about our world.    You can join in the crowd sourcing process here 

An AI System Captions Cartoons

In the CACM:     I note that this is in part solved by crowdsourcing, not by a computer understanding humor.   But the integration of the crowdsourcing into the solution process is interesting,  We used the Mechanical Turk system in this way.  Use for choosing advertising copy/captions?    Interacting with consumers to tag their sentiments?

" ... Microsoft researchers aim to teach artificial intelligence (AI) software how humor works by training it on an archive of New Yorker cartoons and entries into the magazine's cartoon caption contest. Researcher Dafna Shahaf fed the cartoons and contest entries to the software and taught it to select the funniest choices among captions that make similar jokes, relying partly on crowdsourced input from contract workers via Amazon.com's Mechanical Turk. Ranking jokes was the next step, requiring the researchers to manually describe what was happening in each cartoon, and to categorize its context and anomalies.   ... " 

Facebook Analyzing Your E-Laughs

In Wired:  Is this a way to segment people for engagement?   How about linking it to images of the author?  Which Facebook may also be tagging.  Creepy factor? " ... To likely no one’s surprise, the most common expression of e-laughing is “haha” followed by emoji. Facebook goes deeper yet into the nuances of who uses what sort of online laugh: ... Age, gender and geographic location play a role in laughter type and length: young people and women prefer emoji, whereas men prefer longer hehes. People in Chicago and New York prefer emoji, while Seattle and San Francisco prefer hahas. .. " 

The Snarkiness of Google AI

Is humor usefully creative?  How do we utilize it when it is used in creative interactions between human and machines?  Google's examination of the idea.

More Humor at Work

More from Andrew Tarvin on Humor at work.  Why does humor matter?: The infographic.  Again see his site for much more.   Always liked the idea, but it is harder than you think to make it happen. Andrew has the insight.

Humor at Work

My former colleague Andrew Tarvin does a TED talk on Humor at work.  Also on Facebook.  He is now the head Humor Engineer at Humor that Works.  He did podcasts at P&G.   Nice idea for the enterprise, but has rarely been done well.

Dilbert in the Enterprise

In the HBR:   We were heavy users of the Dilbert strip in the enterprise.   They found their way into many slide shows.  We thought that Scott Adams must have been attending our meetings to get the corporate richness of his humor.  More about the comic strip and its origins.

On Who and Whom

In the Language Log:  On Who and Whom.  I had read somewhere else that the distinction between these two are disappearing, based on written word  analyses.  Here he reprints an article in the New Yorker that has James Thurber discussing, humorously, the distinction and how to deal with it.  Language is fun.

Science of Humor

Mind Hacks on the science of humor.    Another example of non conscious reaction.  And what better engagement for retail than laughter?  How can this result purchasing behavior?  Brand engagement?    Links to a Ted talk by Sophie Scott that I have not seen yet.