New tools predict when users will reject new technology

There is something paradoxical about its relationship to technology. We have a very high hope that new technology will solve the biggest challenges of our time. At the same time, we are often skeptical of using new technology solutions.

When new technology fails, it’s not because it doesn’t always work as intended. Sometimes people simply don’t want to use it. Some researchers believe this should be predictable.

Saran Shayf, NTNU researcher at PhD Gjøvik, believes it is important to be able to predict which of the two scenarios will play.

“If people can’t predict whether or not they will adopt new technology, they can result in significant losses in both time and money,” he says.

Shaikh and his colleagues have developed a tool designed to prevent this from happening. This work is published in Journal Data.

Expensive border control technology is not a hit

Shaikh and his colleagues were tasked with investigating why the new technology recently installed at airports and border intersections across Europe is so unused.

Travelers are used to having people check their passports when we travel. New technology channels people through a set of barriers. Your passport and fingerprints are scanned, and the computer compares the passport photo to your face. If everything is in place, the barrier will open and allow it to pass to the other side.

The EU has invested millions of euros to automate border control. A few years after the technology was installed and made available in most of Europe, many travelers still choose not to use this expensive technology.

“It’s hard to imagine something simpler and more efficient. Why do many still prefer manual checks?”

Therefore, the EU committee sought help from researchers to understand why this is true and how to avoid it in the future.

It’s more than just technology

“Before we developed a tool that predicts whether a technology will be used, we had to understand the most important factors in determining whether someone would use a particular technology,” explained Shaikh.

And it turns out to be far more than just the technology itself.

By interviewing users of automated border controls and border guards who operate them, the researchers identified three key factors that determine whether travelers should switch to using new technologies.

User Profile: How old is the user? What kind of sex do they have? What level of education do they have? Is that a veteran traveler or is it your first time? User Recognition: How did users feel after using technology? Was it a positive experience? Or did it cause negative emotions like stress? Has the person used technology in a good way? Surroundings: What does it look like when a traveler decides to use technology? Are there long queues? Long wait? Does using technology seem simple and seamless, or does it feel like a tedious process?

Lots of data from social media

In addition to interviews from five pilot studies around Europe, researchers obtained many valuable data from online discussions.

“We also collected and analyzed a large amount of data from social media. We then compared the data to what we had already collected from interviews. We found that what was discussed online was pretty much in line with the experiences reported by border guards,” said Shayf.

“The big question was whether the outcome could be generalized and applied to technologies that were not yet present or deployed,” he said.

Make data available to other researchers

The goal is for those who develop or introduce new technologies to have access to tools that allow them to assess how the technology may be received.

“Based on this information, they will be able to make more informed decisions about whether to move the technology forward,” Shayf said.

To test whether this was possible, researchers used machine learning to train models based on the data they collected.

This model has already been tested at several automated border intersections across Europe. This allowed researchers to predict whether travelers who had never used the new boundary control before would choose an automated option or a manual option.

So far, the results suggest that the results can be generalized to apart from the original dataset, suggesting that the model can already predict with high accuracy the degree to which the technology will be used compared to previous methods.

Shaikh hopes other researchers will utilize the published datasets for him and his colleagues.

“When we started studying this, the lack of data was one of the biggest challenges we faced. We published two data sets that we had never been able to use before. Researchers and other stakeholders could use them to train even more sophisticated and accurate models in the future,” says Shaikh.

The interdisciplinary research group was developed by Pett. Professor Sule Yildirim Yayilgan, Associate Professor Erjon Zoto, and researcher Mohamed Abomhara were also on Shaikh’s team. Shaikh’s research is based on the Meticos project.