Register now for your free virtual pass to the Low-Code/No-Code Summit on November 9. Hear from executives at Service Now, Credit Karma, Stitch Fix, Appian and more. Learn more.
Gaining insight into how users experience and use software was previously only possible by having all user tests done by people. With the advent of modern sentiment analysis and machine learning (ML) techniques, more insight than ever can be gained through testing.
User Testing is one of the pioneers in the space that uses ML techniques to help discover and analyze user behavior. The past two years have been a whirlwind of activity for the company. In 2020, UserTesting raised $100 million in funding and a year later, in 2021, the company went public on the New York Stock Exchange (NYSE) under the symbol USER.
Today UserTesting announced that it has entered into an agreement to be acquired for $1.3 billion by Thomas Bravo and Sunstone Partners. When the deal closes, the plan is to merge UserZoom — which Thoma Bravo acquired in April 2022 — with UserTesting, to create an even wider set of user experience testing capabilities.
“We’re in a space where we’ve built a suite of technologies for capturing a type of feedback that we call a customer experience story,” Andy MacMillan, CEO of UserTesting, told VentureBeat. “UserZoom has a range of additional different techniques and research methodologies that can complement some of our customer experience stories.”
Event
Top with little code/no code
Join today’s leading executives at the Low-Code/No-Code Summit virtually on November 9. Register for your free pass today.
Register here
How UserTesting integrated ML
Over the past two years, UserTesting has made significant investments in technology that enables it to extract insights from its testing.
Testing involves recording users to see how they interact with applications, including what they click on, and letting users share their experience. MacMillan said his company has invested in using ML to gain insight from the recorded content of the user experience.
“We’re taking really unstructured content, but making it something structured,” MacMillan said. “We trained a series of machine learning models to help discover what we call the moments of insight.”
The moments of insight are those nuggets of information that can help identify trends that will improve the user experience. UserTesting uses multiple ML technologies, including natural language processing (NLP), computer vision, and intent and behavior analysis.
One of the things ML makes possible for UserTesting is the ability to perform click path analytics, which can track where a user goes and what they are actually trying to do when they click on something. User sentiment analysis is another key feature that ML helps with, as is the ability to see if the user is happy with an experience.
UserTesting takes it one step further and uses ML to enable a visualization that overlaps intent and path behavior to understand how people move through a site or application.
“There are a lot of things we can determine about the behavior that we see people exhibiting as they go through a process,” he said.
The Virtuous Cycle of ML
ML does not exist in a vacuum; by definition, these are machines that learn from data.
MacMillan explained that ML’s UserTesting approach is a virtuous cycle, constantly validating and expanding the models his company builds with new data from user testing sessions that already benefit from ML. He added that the ability for people to validate ML models with their own eyes helps build trust in the models.
“We collect these customer experience scenarios — sort of end-to-end videos — and we use the machine learning models to point people to the moments of insight,” MacMillan said. “But you can always dive in. You can always say ‘oh the model says this, let me see some of this customer experience story’, and see if the intent really matches the sentiment.”
One of the biggest challenges in ML for any organization, according to MacMillan, is having the right kind of training data. UserTesting already has video recording, which shows what is happening on a screen, and the test also collects click data from the users. The tests are run against a test plan, so there is a basic expectation for what users should do. UserTesting has dedicated staff who also label content as part of their day-to-day work to help train and optimize the models.
“The goal of the product is to connect teams directly with real customers and real people to get human insight out of the product,” MacMillan said. “We think machine learning is really just a means of helping people connect to those moments of insight, but those moments are still human.”
The mission of VentureBeat is a digital city square for tech decision makers to learn about transformative business technology and transactions. Discover our briefings.
Janice has been with businesskinda for 5 years, writing copy for client websites, blog posts, EDMs and other mediums to engage readers and encourage action. By collaborating with clients, our SEO manager and the wider businesskinda team, Janice seeks to understand an audience before creating memorable, persuasive copy.