Top

Artificial Intelligence and User Experience

Ask UXmatters

Get expert answers

A column by Janet M. Six
November 18, 2019

In this month’s edition of Ask UXmatters, our panel of UX experts discusses how UX design for artificial intelligence (AI) applications differs from designing a traditional application. A panelist warns the questioner about the dangers of over-relying on artificial intelligence instead of defining a product that truly meets users’ needs.

Our experts then consider the role of User Experience in the creation of AI applications—especially those that rely on machine learning (ML). Their discussion ranges from the importance of user advocacy, the value of doing user research, how to avoid bias, defining high-quality training data, transparency to users, and gaining user trust by ensuring that the user feels in control of an AI application. This column concludes with a brief discussion of the need for UX design best practices for AI applications.

Champion Advertisement
Continue Reading…

Every month in my column Ask UXmatters, our panel of UX experts answers readers’ questions about a broad range of user experience matters. To get answers to your own questions about UX strategy, design, user research, or any other topic of interest to UX professionals in an upcoming edition of Ask UXmatters, please send your questions to: [email protected].

The following experts have contributed answers to this month’s edition of Ask UXmatters:

  • Pabini Gabriel-Petit—Principal Consultant at Strategic UX; Publisher, Editor in Chief, and columnist at UXmatters; Founding Director of Interaction Design Association (IxDA)
  • Adrian Howard—Generalizing Specialist in Agile/UX
  • Janet Six—Product Manager at Tom Sawyer Software; UXmatters Managing Editor and columnist
  • Andrew Wirtanen—Lead Designer at Citrix

Q: Do you have experience doing UX design for an AI application? How is it different from working on a traditional application?—from a UXmatters reader

“For the most part, it isn’t different,” answers Adrian. “All of the core UX design tasks—understanding the people who would use the product, their objectives, their painpoints, and the ways the product can help them—remain the same.

“The very fact that some folks think AI projects are significantly different from other UX design projects is actually one of the danger points. Some teams get carried away by the technology and start thinking the AI capabilities alone are going to persuade people to use the product. But they won’t—unless the product actually solves customers’ problems effectively.

“If the AI doesn’t solve the customer’s problems well, that truth can be hard for the rest of the organization to hear—especially if they’ve placed all their bets on their product’s AI capabilities. So you’ll need to use all your facilitation and persuasion skills to ensure that the outcomes the customer wants are front and center throughout the product-development lifecycle.”

The Role of User Experience in Creating AI Applications

“When designing an AI application, the UX designer’s role of user advocacy takes on greater importance than ever before,” advises Pabini. “Some key contributions that User Experience can make to an AI product-development project include the following:

  • conducting generative user research—By conducting user research, UX researchers and designers can ensure that a product team develops a deeper understanding of the audience for an AI application, as well as the needs and behaviors of potential users. Their research findings reflect the human experience and provide the reliable qualitative data that should be at the foundation of any AI application. Gaining this understanding can also help reduce product-team members’ inherent bias and ensure that the team chooses the right training data for machine-learning algorithms.
  • defining training data—The experience information architects and UX designers have of defining metadata for information on the Web translates quite well to defining the training data for machine-learning algorithms. In addition to leveraging quantitative data, training data should rely on learnings from qualitative user research. Information architects and UX designers are accustomed to creating design solutions that are based on findings from user research and appreciate their value. A machine-learning application is only as good as its training data.
  • gaining users’ trust—As user advocates, UX professionals understand that it is essential to gain users’ trust—when designing any application, but especially for an AI application. Design solutions that offer transparency and give users control over their personal data make it much more likely that users will trust an organization enough to provide the data that drives many AI applications—especially the machine learning that supports personalization.

“We recently published an article by Robert Schumacher and Gavin Lew—a frequent contributor to Ask UXmatters—titled ‘Artificial Intelligence, Supervised Learning, and User Experience,’ which explores some issues relating to this discussion in depth.”

“Another area in which UX skills can help is in combating bias,” suggests Adrian. “The problems that arise from biased training data are common and well known. Take a look at Karen Hao’s MIT Technology Review article ‘This Is How AI Bias Really Happens—and Why It’s So Hard to Fix.’ Our user-research practices and awareness of cognitive biases can sometimes be very useful in helping organizations to understand issues of bias and bring them to the surface within an organization.”

Setting Clear Goals for AI Applications

Even as development teams use AI in more and more applications, a common misunderstanding persists: That an AI technique that is successful in one arena can be applied in a different arena and result in similar benefits. Unfortunately, this is not true. Companies build AI systems with specific goals in mind—for example, to discover fraudulent transactions, filter out spam email messages, recommend products on a retail Web site, or recognize speech. The AI algorithms that find fraudulent transactions won’t be helpful in recognizing spoken instructions.

AI systems generate very focused results, so it is important to define the nuances of the system goals in detail. The first thing a UX designer can do to support the creation of an AI-assisted product is to ensure that a product team is building an AI system with the correct goals in mind. It is vital that the team has clear goals. Otherwise, the system might find the right answers to the wrong questions!

One way in which UX designers can assist in the creation of AI-assisted applications that leverage machine learning is to vet the training data or user feedback. In addition to building an AI system with the correct goals in mind, it is critical to provide good training data to the system. Garbage in, garbage out. If the training data does not match what the system would encounter in real life, it is unlikely that the system would perform well in use. UX designers can help AI designers to create or find effective training data by establishing a better understanding of the user, their scenarios, and their data, and thereby help AI-assisted applications to perform significantly better.

Design Best Practices for AI Applications

“Best practices for designing artificial-intelligence applications are still developing, so it is crucial for the UX community to share how we are leveraging and designing for these new capabilities,” replies Andrew. “Recently, I’ve been seeing more examples of using machine learning to enhance the user experience. For example, in Google Drive, the Quick Access feature suggests several documents that the user might want to open. By default, the user’s recent actions determine the order in which documents appear in the Quick Access section. But over time, the system might make suggestions based on frequency of use, time of day, the user’s location, or permissions that the user grants to the system.

“One of the most critical design heuristics for AI-driven applications is the necessity of being transparent with the user. We must keep the user informed of AI-driven decisions and allow the user to maintain control.” 

Product Manager at Tom Sawyer Software

Dallas/Fort Worth, Texas, USA

Janet M. SixDr. Janet M. Six helps companies design easier-to-use products within their financial, time, and technical constraints. For her research in information visualization, Janet was awarded the University of Texas at Dallas Jonsson School of Engineering Computer Science Dissertation of the Year Award. She was also awarded the prestigious IEEE Dallas Section 2003 Outstanding Young Engineer Award. Her work has appeared in the Journal of Graph Algorithms and Applications and the Kluwer International Series in Engineering and Computer Science. The proceedings of conferences on Graph Drawing, Information Visualization, and Algorithm Engineering and Experiments have also included the results of her research. Janet is the Managing Editor of UXmatters.  Read More

Other Columns by Janet M. Six

Other Articles on Artificial Intelligence Design

New on UXmatters