NLP is Our FORTRAN

A person writing a math equation on a whiteboard.

Remember the movie Hidden Figures?

The whole movie is phenomenal. One part in particular sticks with me. Dorothy Vaughan (played by Octavia Spencer) watches the state-of-the-art, room-sized IBM mainframe being delivered to her workplace at NASA. Dorothy, who supervises of a team of human computers (as they're called in the '60s), instantly realizes their world will change.

She starts to learn how to program the mainframe in FORTRAN. Not only that, but she prepares her team to work the IBM computer as well.

Dorothy is not only a mathematical genius, but a savvy technologist and exemplary manager.

Because of her talent, Dorothy would enjoy a long and distinguished career at NASA. Certainly not as long nor distinguished as she deserved, however, due to the headwinds of racial and gender discrimination she had to work against.

NLP and us

A while back someone on the UX + Content Slack asked the most basic question:

"What's the future of content design?"

It made me think about NLP.

NLP stands for Natural Language Processing, a term for using an artificially intelligent algorithm to generate language.

I had always dismissed NLP tools as incompetent writers.

Then last year, I started to think, “What if?” I Googled NLP and was astonished at what I found.

Enter GPT-3

I'll link a bunch of articles about GPT-3 at the end, but here are the basics you need to know:

• Let’s get the acronym out of the way: GPT-3 stands for "generative pre-trained transformer 3."

• It was created by OpenAI, a research lab founded by Elon Musk, among others.

• GPT-3 was trained on a 175-billion-parameter dataset. I won't get into what a parameter is. Just know that's 10 times more data than the next largest NLP model that existed when GPT-3 was released.

So it uses lots of data, but does it write like a human? Here's an example of text that GPT-3 has written:

“Critics hope to refute what they consider as being the naivety of my voice. Yet there is more here than meets the eye! As Mahatma Gandhi said: “A small body of determined spirits fired by an unquenchable faith in their mission can alter the course of history. So can I.”

Source: “A robot wrote this entire article. Are you scared yet, human?” The Guardian.

If you've ever hired content folks, you know how difficult it is to find humans who: a) want to work with you, and b) are good at language.

The mechanics of grammar and syntax are challenging enough for humans to grasp, much less complexities of narrative structure and clearly conveying meaning.

Yet we now have a bot that can write better than a majority of humans.

Time to learn FORTRAN

My take: in the future, many writing tasks currently performed by humans will be outsourced to algorithms that do them better, faster, and more efficiently.

Heck, I already use those once-annoying response chips in Gmail, LinkedIn messages, and texting apps about 70% of the time. They probably don't even need a model the size of GPT-3 API to automate those messages for me.

That doesn’t mean folks who call themselves content designers, UX writers, interaction designers, and researchers won't have a job in the future. Automation doesn’t eliminate the need for humans. It changes the skills required.

So, what do our jobs look like in a world where writing is automated? Certainly we'll still need to identify our users’ needs, plan solutions, and grapple with our complex organizations, partly to provide context to the machines doing tactical work.

Whether we find ourselves researching use cases, curating training data, designing prompts, or editing completions, the human work of sensemaking continues.

It's in our interest to be like Dorothy, and start figuring out what that work looks like with tomorrow's toolset.

This essay was first published in my email newsletter, Philosophy & Practice. If you want more of this type of content in your inbox, subscribe below.

Helpful Conflation

A diagram showing writing as a subset of designing.

It seems strange that we can sometimes refine ideas by conflating them with other ideas.

I’ve been thinking about two examples this week.

1. Writing = designing

This phrase “Writing is designing,” popularized as the title of an indispensable book by Michael Metts and Andy Welfle, encapsulates an important, long overlooked truth. As Jared Spool has said:

"Design is the rendering of intent."

We can manifest our intent by designing house interiors, building structures, cars, cartoons, and websites. When we define design broadly like this, writing is a subset of designing. We use our (UX) writing skill to render our intent in the communications of a digital product.

This isn't exactly equivalence. We're not really saying that writing and designing are exact synonyms. What we mean is that writing is a type of designing.

2. Content = product

Next we turn to the rampant under-resourcing of content in tech organizations and compare it to the (more} adequate resourcing of engineering teams. We can theorize that the leaders at software companies have a greater understanding of the value of engineering than content. So they organize their product teams by allocating engineers with the necessary skillsets.

Content, on the other hand, is less familiar to tech leaders, and is perceived as less valuable than code. Content-heavy properties have long fallen under the domain of marketing (blogs, email, notifications) or documentation (knowledge bases) so they aren't categorized as software products.

Since the product is the atomic unit of the software company, the content that flows between, through, and from products becomes invisible. And, as a result, under-resourced.

Could we change this by encouraging our companies to define their content as a product?

I like this response Michael Andrews gave when I posed the question on Twitter:

A tweet saying, “Yes, I believe it can be beneficial to embrace widely used corporate process/management frameworks to ensure our initiatives and projects are sustainable and enable them to evolve.

It's really about defining our work in terms that our teams will understand and value.

A diagram showing content as a subset of product

Conflation as connection

In both of these scenarios, we're not creating exact equivalences. We're defining one thing (writing, content) as a subset of something else (designing, product). We're drawing analogies, making connections.

Often in our work we value distinctions. We must slice and dice words to get to the most specific possible meaning.

Distinctions are necessary in our work, but when we want to communicate value outside of our communities, we often have to collapse these distinctions into larger, more understandable categories by connecting them with other familiar ideas.

We have to conflate to be helpful.

UX Unicorn vs. UX Team: Which Is Better?

Jakob Neilsen explaining that an Olympic javelin-throwing “specialist” outperforms an Olympic decathlete at javelin throwing.

I’ve been thinking a lot about collaboration on design teams.

Even though lots of data is now available proving that teams of specialists deliver better results than a single practitioner with skills in multiple disciplines (often dubbed a “unicorn”), it’s still common to see projects and products whose entire design process is the responsibility of one designer.

This short video by Jakob Nielsen provides a great quick argument that a team of specialists will outperform a single generalist.

I love the example about the performance of the decathlon athlete vs. the “specialist” or single-event athlete.

As a potential counterpoint, this article by Conor Ward at first appears to argue against teams of specialists and for the “unicorn” approach.

A quick read, however, shows that Conor isn’t proposing that one person handle all the responsibilities of designing a product. He still posits a team. He just argues that each person on the team should be highly skilled in all UX functions—design, content, research, information architecture, development.

This arrangement would be a collaboration of unicorns, which he also calls “square-shaped designers” (which creates a pretty funny mental picture).

I think both takes are true. Designing products is complex. We need teams of specialists.

If each specialist is also a “unicorn,” highly skilled in all adjacent disciplines, that’s great! Such a practitioner would be difficult to find (I wouldn’t count on hiring all unicorns), but if you have them available, so much the better.

5 Essential UX Research Terms that Teams Should Know

Person writing on a sticky note posted on a wall

Whether you’re a user experience (UX) designer, content designer, front-end developer, or aspiring UX researcher, understanding UX research is essential to your work. You have to understand your users in order to help them meet their goal or accomplish their task.

If you’ve done any reading on UX research, you’ll notice there’s quite a bit of jargon. For those new to UX, I thought I’d list the 5 terms that I think are most essential for aspiring and new UX practitioners to know.

Generative research and evaluative research

One way to look at UX research is by phase of the product design process.

• In the beginning, research may be more generative. That means you’ll be gathering information about your user, how they operate, and what’s important to them. These findings help you generate ideas (thus the name).

• Once you have enough information for your team to design a concept, you can conduct evaluative research. This is where you put the design in front of users to see whether they can use it.

Keep in mind that the best evaluative research is task-based. You ask the user to reach a goal or accomplish an action. You ideally don’t put a design in front of them and say “what do you think?”

Qualitative research and quantitative research

Another way to divide up your research activities is not by when you do it, but how.

• Qualitative research delivers findings that typically aren’t numerical. This type of research includes user interviews, ethnographic studies, diary studies, card sorts, and tree tests.

• Quantitative research is just what it sounds like: research that gives you numerical data. Examples include A/B testing, surveys, and analyzing analytics.

Affinity mapping

Affinity mapping comes after qualitative research. You summarize your findings, sometimes collaboratively as a group, often writing each finding or theme on a sticky note. Then you arrange the stickies by larger themes or connections between the ideas.

Popular tools for virtual affinity mapping include Miro, Mural, Figjam, and Plectica.

What research concepts are the most important to you? Comment and let me know.

The Best Podcasts for UX Folks

A microphone set up in a large room.

I have a confession to make:

I’m a podcast junkie.

It’s true. I love podcasts to an almost unhealthy degree. I’ve experienced that “driveway moment” (when you don’t want to get out of the car until you finish the podcast episode) too many times.

(Oddly, when I tell non-podcast people that I love podcasts, they ask the same question: “When do you listen to them?” To which I always answer: “When I’m driving or doing housework.” Obvious, no?)

Anyway, I recently came across a request on Slack for the best UX podcasts. So here’s a list of the best podcasts I know of, with an emphasis on podcasts about content design, UX writing, and usability research.

• Awkward Silences by User Interviews. Focused on UX research, this podcast has possibly the best title ever.

• Cautionary Tales by Tim Harford. Don’t be put off by the fact that it’s not, strictly speaking, a UX podcast. Tim talks about “mistakes and what we should learn from them” by telling memorable and educational stories.

• Cognitive Bias Podcast by David Dylan Thomas. We’re all subject to cognitive biases, so we should be aware of them. Will that help us avoid them in the future? Maybe, maybe not. Either way, Dave makes learning about them fun.

• Content Strategy Insights by Larry Swanson. Larry knows everyone in UX content. His podcast features fascinating guests and incisive questions.

• Content Strategy Podcast by Kristina Halvorson. Super-insightful interviews with experts in UX content. You might end up listening to some episodes multiple times.

• Efficiently Effective by Saskia Videler. Although this podcast hasn’t been updated lately, Saskia’s interviews with UX content pros hold evergreen bits of wisdom.

• UX Tea Break (video) by David Travis. David’s a true guru who can make any UX research topic (even technical ones like eyetracking) interesting and understandable.

• What’s Wrong with UX? by Laura Klein and Kate Rutter. I’m a little biased because I work with Laura, but her conversations with Kate are hilarious and enlightening.

Do you have a favorite UX-related podcast? Comment and let me know!

The ROI of Content Design

Sometimes numbers are your friend.

Someday, you may need to get executive buy-in to hire a Content Designer (or UX Writer or Content Strategist, depending on what your org calls it). You’ll find that some stakeholders respond to stories, some to best practices, and some to metrics.

While it may seem self-evident that our work has value, in the past it was tough to find data quantifying the business value of our work.

But recently, industry experts started publishing more stats. So I started collecting them.

Here’s a list of the ROI metrics I was able to find. I hope you find it useful.

1) Content strategy raises net traffic 56% for Facebook

In the foreword to Kristina Halvorson’s book Content Strategy for the Web (page xii), Sarah Cancilla reports that her work on a specific content module at Facebook resulted in a 56% increase in traffic to that content and 6 million more users engaged in finding friends. Here’s a short excerpt:

2) Content design increases task completion for the UK government by 88%

In an article from 2018, Sarah Winters reports on content design work that turned a 100% failure rate (0% completion) into 88% completion.

3) Content design at Microsoft boosts product NPS, task completion, and usability

In an interview with Larry Swanson, Kylie Hansen, Director of Content Design at Microsoft, reports that her team was able to measure the following impacts of content design:

• NPS increased 8 points

• 44% of task failures solved

• usability increased 92%,

• unquantified improvements in numbers of active users and retention

4) Removing one button brings in $300 million more revenue

Sometimes, removing elements of a design is the most effective tactic. Jared Spool writes that removing an unnecessary button from a checkout flow resulted in 45% more sales for his e-commerce client ($300 million revenue in the first year).

5) Expedia gains an extra $12 million for simplifying a form

Similarly, Expedia found that removing an unnecessary form field resulted in an additional $12 million in revenue.

6) Customers don’t buy for lack of needed content

Not only does good content design bring in more revenue; the inverse is also true. Bad (or lack of) content design costs organizations money.

From the UK, CSM, The Magazine for Customer Service Managers & Professionals, reports that "one in three have acted on their frustration by abandoning a purchase because they couldn’t find the information they needed."

7) Bad content design costs Citi $500 million

This is a real gem. Due to the absolutely horrifying UX of its software—including cryptic field labels and a warning modal that provided no useful information—Citi’s operations team mistakenly transferred $900 million to creditors. Of that sum, $400 million was voluntarily returned. As for the other $500 million, a court ruled that the creditors could keep it.

Your turn

These are the ROI metrics I found by scouring the Internet, talking to folks, and researching content design.

What about you? Do you have metrics that belong on this list? Let me know!

IA for AI: Why Chatbots Require Information Architecture

A curious idea has been circulating online: that experiences powered by artificial intelligence (AI) don’t require information architecture (IA) or design work. 

That idea is wrong.

Perhaps it arises from the fact that many AI experiences don’t involve screens like traditional apps and websites. If there’s no screen (the reasoning might go), there’s no visual design. And no visual design means no information architecture needed!

However, our own experience and many content strategy experts tell us that, screen-based or not, all digital experiences include content (or information). And where there’s information, you need some amount of information architecture. 

For example, Mike Atherton and Carrie Hane encourage us to create what they call future-friendly content. Doing this allows information “to be reused across all hardware devices and software platforms.” Even hardware and software that integrate with AI and don’t use a screen for user input and output. 

That means all digital experiences, including AI-powered ones, require IA. But what does that IA look like? 

Let’s check out a few types of AI experiences and the information structures we can build to fuel them.

Types of AI experiences

Definitions of what exactly constitutes artificial intelligence vary, but for our purposes, we think of AI as linked to machine learning (ML). Machine learning happens when a program is capable of “learning” from experience and changing its output to more closely meet its goal.

(That’s a pretty broad definition. But notice that we don’t say that AI engines “think” or “understand” what we tell them. Human-level intelligence is way beyond the ability of even the most sophisticated AI algorithms, for now.)

Let’s look at three types of AI experiences and what information architecture might look like for each one.

Rule-based AI systems

The simpler type of AI algorithm is the rule-based system. Many chatbots today are rule-based. That means that a content designer writes a conversation script, which the program then follows. 

At this point, you may object: “That’s just a regular computer program. It’s not AI.” You’re right; a chatbot can be powered by a traditional computer program (remember Clippy?). A rule-based chatbot would only rightly be considered AI if machine learning allows the program to teach itself something at some point in the processing—for example, deciphering text from speech and learning from that process. 

In 2016, my colleague Whitney French wrote about this type of AI system: 

The bot’s UI is simply a conversation made up of different paths the user could take. We can visualize it as a conversation tree. Each point of friction from our exploration phase maps to a branch on our conversation tree. If it’s starting to look familiar, that’s because it’s just like a product or site map, with each conversational branch representing a feature set.

IA for rule-based systems: applied to a chatbot, Whitney called it a conversation tree. Applied to a website, we call it a sitemap. Image: WillowTree.

Learning systems

It makes sense that a rule-based system has to be designed—has to have its information architected, if you will. But what about more sophisticated systems that move beyond explicit rules toward real learning?

Again, to make the example concrete, let’s imagine a chatbot, but one that doesn’t follow a conversation script. Perhaps it uses natural language processing (NLP) to attempt to provide an appropriate response to your question. 

Such a bot could work by recognizing keywords (and their synonyms) in your request, classifying your request by topic, then selecting a response from a list. 

View fullsize

You can use an intent classification algorithm to craft an effective chatbot, such as the Domino’s Pizza bot on Facebook Messenger. Click to enlarge.

This type of learning chatbot still requires IA: 

• It imposes structure on input data. Perhaps the chatbot even gives the user suggested responses to tap, helping to ensure a good experience by keeping the conversation on a topic the bot can handle. This data structuring is programmed to meet the required architecture of the bot’s input data.

• It uses a classification scheme, or taxonomy. For example, perhaps the Domino’s bot has separate categories of responses for a pizza order, a pasta order, a drink order, or a customer service question like, “When is my pizza going to arrive?” These categories comprise an IA. As Seth Earley states, “These classifications qualify as a foundational element of information architecture.”

IA for very advanced algorithms

It’s easy to see why simple machine learning algorithms require information architecture. But perhaps you’ve heard of very advanced algorithms, such as GPT-3, built by openAI. Its output is sometimes indistinguishable from human writing. 

View fullsize

GPT-3 can write an article that reads like it came from the keyboard of a travel blogger—more or less. Bold text is my prompt. Click to enlarge.

To become such a good writer, we know that GPT-3 had to draw on an advanced neural network trained on a vast corpus of data from the Internet. We really don’t know what types of data structures, or information architecture, GPT-3 employs in its mysterious black box of an algorithm.

Yet we can tell that even this advanced algorithm does require some type of information architecture. At a minimum, my prompt (user input) must provide the proper structure to allow the algorithm to correctly predict (and create) the output I want.

If I structure (or “architect”) my prompt differently, I receive a different output from GPT-3. Click to enlarge.

IA is essential to AI experiences

Product designers, content strategists, and information architects know that the more work we take on crafting a seamless user experience, the less work the user has to do to interact with the software we’re designing.

Software powered by AI is no different. Perhaps our tasks will change as we tackle more AI challenges in the coming years. But design and IA will always be necessary to building effective, user-friendly AI experiences.

(Thanks to my WillowTree colleagues, especially Laura Massengill, for providing input and edits to this article.)

The Massive List of Content Design & UX Writing Resources

Seven years ago, Jon Colman published his indispensable “Epic list of content strategy resources.” In it, he compiled over 400 articles, books, newsletters, and more for aspiring content strategists to reference and learn from.

Over the past seven years, a couple of related concepts have risen to prominence: content design and UX writing. And while these three practices (content strategy, content design, and UX writing) aren’t exactly the same, they’re closely related.

Since Jon has already done the hard work of creating a foundational list of resources for content strategists, I decided to shamelessly steal—I mean, build on—his idea to provide a list for folks interested in learning about our field. With the twist that my list is focused on the fields of content design and UX writing. 

If you’re new to content work, please do yourself a favor and check out Jon’s list. It’s a great snapshot of the state of the practice of content strategy circa 2013, and contains links to many foundational works that you’ll derive great benefit from.

First read: Jonathon Colman’s article: “Epic list of content strategy resources”

Books

(Note: This section contains affiliate links.)

• Content Design, Sarah Richards

• Strategic Writing for UX, Torrey Podmajersky

• Writing for Designers, Scott Kubie

• Writing is Designing, Andy Welfle & Michael Metts

• Why You Need a Content Team and How to Build One, Rachel McConnell

• Nicely Said, Nicole Fenton and Kate Kiefer Lee

• Letting Go of the Words, Ginny Redish

• Lead with Content: How to Put Content at the Centre of Digital Transformation, Padma Gillen

• Microcopy: The Complete Guide, Kinneret Yifrah

• Designing Connected Content, Carrie Hane and Mike Atherton

• Conversational Design, Erika Hall

• Word Up!, Marcia Riefer Johnston

• UX Writing Basics, Marie-Pier Rochon

Articles

• “What is content design?” by Sarah Richards, Content Design London

• “What is content design?” at Gov.UK

• “What is content design?” by Becky Hirsch

• “What is content design?” by Carrie Hane

• “What is content design?” by Michael Andrews

• “What is UX writing?” by Lisa Sanchez

• “What is UX writing?” by Bobbie Wood

• “What is UX writing?” by Kristina Bjoran

• “On content design at WillowTree” by Rachel Thomas and Melanie Seibert

• “Designing a name” by Clay Delk

• “Why we’re moving from content strategy to content design” by Elisabeth Carr

• “We’re changing our name to content design” by Meridel Walkington and Betsy Mikel

• “What is UX writing and why is it suddenly so popular?” at UIUX Trend

• “New thinking: Brain Traffic’s content strategy quad” by Kristina Halvorson

• “Content designer,” Wikipedia

• “How to spot good content designers” by Rachel McConnell

• “Content design: a great way to make user-centered content” by Edwin Toonen

• “5 principles of good content design” by Ksenia Cheinman

• “Seven principles for effective content design” by Rachel McConnell

• “So you’re a content designer… what next?” by Rachel McConnell

• “What does a content designer do all day?” by James Reith

• “What we mean when we talk about content design” by Sarah Richards

• “UX writing, UX copywriting, content strategy, and content design are not the same job” by lauxcritora

• “What does a UX writer actually do?” by Yuval Keshtcher

• “10 things UX writers hate to hear” by John Saito

• “16 rules of effective UX writing” by Nick Babich

• “Why every writer should learn UX writing” by Laurah Mwirichia

• “The UX writing starter kit” by Alysa Yamada

• “How to create a UX writing portfolio” by Andrea Drugay 

• “How to build a better product with UX writing” by Anastasiia Marushevska

• “The ROI of UX writing” by Kinneret Yifrah

• “The rise of the UX writer” by Emily Stevens

• “Why your design team should hire a writer” by John Saito

• “Designers and writers should co-design product experiences” by Felicia Wu

• “The ABCs of content design” by Kate Cooper

• “What’s the role of content management in digital products?” by Michael Andrews

• “Finding your way as a UX writer” by John Collins

Websites

• Mailchimp Content Style Guide

• The UX Writing Library

• UX Writing Hub

• UX Writing Mentors at UX Coffee Hours

• Writing Principles at Google Material Design

• UX Writer at Google Design Jobs

• Content + UX Resources

• Readability Guidelines by Content Design London

Talks

• How we destroyed content design by Jonathon Colman

• Content design: what it is and why you need it by Erin Abler

• What is a content designer? by Craig Jamieson

• What is good content design? by UK Government Digital Service

• What is content design? by Padma Gillen

• Content-first design by Steph Hay

• Content design for the conversational interface by Melanie Seibert

Courses

• UX Writing Fundamentals

• Microcopy & UX Writing Course

• Use Your Words

• Writing is Designing Workshops

• Training from Content Design London

• UX Writing from Berghs School of Communication

Social media

• Slack: Content + UX

• Facebook: Content Strategists 

• Facebook: Microcopy & UX Writing

• Pinterest: Good Job, Microcopy!

• Content Strategy Community

Conferences

• Content by Design

• Confab

• Button

• Plain Language Summit

• UX Writer Conference

• Design & Content

Podcasts

• Content Strategy Interviews: Sarah Richards

• Writers in Tech

• Writers of Silicon Valley

Did I miss anything? Contact me and let me know!