People More Likely To Trust Robots That Sound Like Them

People prefer robots that speak in the same accent as them, a new study has found.

Researchers discovered that some people found robots more trustworthy and competent when they spoke in their dialect as opposed to with a more standard accent.

In an experiment, Germans from the capital city Berlin listened to robots speaking to them in different accents.

The results showed that those more familiar with the Berlin dialect preferred it when the robot spoke to them in that accent, whilst those less accustomed to the dialect preferred a more standardized language.

The researchers, from the University of Potsdam, said the findings could inform what accents different social robots speak to us in.

Social robots can be used to assist us in a growing multitude of ways across many industries, including in teaching, learning and caring.

These robots are designed to make us feel comfortable, so how they communicate with us is an important aspect to explore.

Research shows that robots function best when the person interacting with them feels they can trust them – and a human-like speaking voice can contribute towards this.

The researchers at the University of Potsdam sought to discover whether speaking to humans in their native dialect or accent would improve their trustworthiness and competence.

“Surprisingly, people have mixed feelings about robots speaking in a dialect,” doctoral student Katharina Kühne, a lead author of the study published in Frontiers in Robotics and AI, explained.

“Some like it, while others prefer standard language. This made us think: maybe it’s not just the robot, but also the people involved that shape these preferences.

“Imagine a robot that can switch to a dialect.

“Now, consider what’s more critical in your interaction with a robot: feeling a connection – think of a friendly chat in an elderly person’s home – or perceiving it as competent, like in a service setting where standard language matters.”

To test the impact of a robot’s dialect on its acceptance by humans, the researchers recruited 120 people living in either Berlin or elsewhere in the state of Brandenburg to take an online survey.

They asked participants to watch videos in which a robot using a male, human voice spoke in either standard German or the Berlin dialect, which is considered working-class.

Like a cockney accent in the UK it is sometimes used by media organisations to give an informal, friendly impression.

“The Berlin dialect is generally understandable to most German speakers, including those who are not native German speakers but are fluent in the language,” Kühne said.

The scientists then asked participants to rate the robot’s trustworthiness and competence and to additionally fill out a demographic questionnaire including details such as age, gender, how long they’d lived in Berlin, how well they spoke the dialect, and how often they used the dialect.

The survey also automatically recorded the type of device participants used to watch the videos: a phone, tablet or computer.

The study team’s results showed that there was a clear link between trustworthiness and competence, with higher perceived competence relating to higher perceived trust levels.

In general, participants preferred the robot speaking in standard German.

However, those more comfortable with the Berlin dialect preferred the robot to speak in that dialect.

The results also showed those who were using a phone or tablet rather than a computer to view the videos tended to give lower ratings to the robot speaking standard German, which the researchers speculated could be because these smaller devices meant they had more distractions and a higher cognitive load, so the trust signal of the standard German had less of an impact.

“If you’re good at speaking a dialect, you’re more likely to trust a robot that talks the same way,” Kühne said of the results.

“It seems people trust the robot more because they find a similarity.

“This leaves us without clear evidence for or against the idea that people facing challenges might find more comfort in social robots speaking in a familiar dialect.

“But if a robot is using the standard language and it’s essential for people to perceive it as competent in the interaction, it might be beneficial to minimize cognitive load.

“We plan to dive deeper by testing cognitive load during conversations.”

Kühne added that speaking or understanding a dialect can be part of an in-group identity, allowing the robots to take advantage of in-group bias.

However, the prestige of a dialect may affect how it’s received by those hearing it.

“Context matters a lot in our conversations,” Kühne concludes, “and that’s why we’re planning to conduct more studies in real-life situations.”

Produced in association with SWNS Talker