can an ai learn
to make you laugh?

 How can computers for professionals in shared work environments inject humor into the user experience and interface to reduce stress and maintain workflow?

the goal 

 I wanted to explore how machine learning could be designed to create effective humor. This research heavy task required addressing many unanswered questions before designing for the big question...

(the remaining 2 minutes of the video, at bottom of this page, explain the final product)

conceptual framework: stress to A.I.

conceptual framework:
stress to A.I.

areas of interest

  • Stress via Work & Tech
  • ML Stress Detection
  • Humor Environments
  • Humor Theory
  • Humor Therapy
  • CUI & Digital Interaction

gathering academic insight

I gathered current knowledge and research surrounding each of the topics.

  • Humor in Environments
  • Therapy with Humor
  • Humorous CUI’s & Digital Interaction
  • Stress via Work & Tech
  • ML Stress Detection

I synthesized the findings to inform the next set of questions, frameworks and design exploration..


Insights:

  • Elevated stress is harmful short and long-term
  • Computers are highest source of stress at work
  • Laughter has many health benefits
  • Smiling/inward laughter improves workflow
  • Five conditional factors for effective humor
  • context
  • style
  • form
  • reference
  • timing


Findings:

  • Many theory about WHY things are funny
  • No theories about HOW to create humor
  • Humor varies by culture even in close proximity

visualizing the research frameworks

Diagraming my findings visually in maps and frameworks is important. It explains their relation to each other clearly to the reader and the flow of concepts as I developed conclusions. It is an accessible foundation to reference the research.

  • Slide title

    Write your caption here
    Button

  • Slide title

    Write your caption here
    Button

  • Slide title

    Write your caption here
    Button

  • Slide title

    Write your caption here
    Button

  • Slide title

    Write your caption here
    Button

  • Slide title

    Write your caption here
    Button

  • Slide title

    Write your caption here
    Button

  • Slide title

    Write your caption here
    Button

humor improves with the company of others

Humor and laughter happen more fluidly in a social setting. I met with multiple groups to brainstorm humorous, silly, and playful ways to address stressful situations on a computer. In some groups we played games to grease the funny gears.


Findings:

  • Jokes required backstory or familiarity
  • Characters and voice were common elements
  • The funniest ideas were the least appropriate


Wish I Had:

  • Used voice transcribing app for all meetings
  • Come up with more specific activities to steer the conversation and avoid unusable material

existing practices of on-screen stress management and humor 

I examined precedents from each of four topics, that reflected on a potential application of the stress, humor and A.I. research performed.


Insights:

  • Stress mgmt and humor therapy apps utilize:
  • light hearted illustrations and characters
  • anxiety and depression treatment tactics
  • required a time investment with questionnaires and long activities
  • Humor apps, widgets and games quickly became predictable

watching pros prime the audience and time the punch

Catching moments of spontaneous humor is virtually impossible to predict. To observe humor and laughing in real time I had to go to  comedy clubs and improv theater, where there was the possibility of a joke "flopping".


Findings:

  • Stand-up comedians used stories and voices to paint a picture for their audience.
  • When expectation for a joke built up, a violation of the situation received more laughs.
  • Allowing time for audience to laugh was very effective.
  • Impersonations and characters used in improv received consistent light laughter.

building personas with unique stressors and sense of humor

To paint the full picture  and maintain consistency I created two office worker personas with different types of stress and unique humor tastes .


  • Persona Stressors by Stage
  • Daily Activity Patterns
  • Personal Cultural References
  • Humor Profiles


The personas were placed in scenarios where they became stressed. The potential interaction and experience was then journey mapped. To show how variation might progress for unique humor preferences over time, I designed humor interventions at three stages of development nine months apart for two personas.

  • 18 humor studies.
  • 9 for each persona.
  • 3 in each of the 3 format categories
  • language
  • games
  • characters


The individual humor AI became much more in tune with the user's stress cycles and indicators for predicting when a humor injection would be most effective.

building humor studies

The next step was to develop what these humor injections would look like, and show how the ML Humor agent would evolve and improve over time.


The humor designs were explainable within ML  criteria,  safe for work, relatable, fresh and brief.


Reflections on making humor :

  • funny concepts don't always translate to the screen well
  • coming up with funny material is very humbling, because jokes tank sometimes
  • a laugh now means a chuckle or smirk later
  • suffer from over-thinking
  • benefits significantly from discussion and riffing


Just as we have AI technology that can see far more from one medical image than the most experienced doctors, I believe AI can eventually be absolutely, sidesplitingly, hilarious....eventually.

see full document - all 18 studies pg.68

You can't teach or learn funny. You have step in it and get it all over your shoe.