robot

(Credit: Alex Knight from Pexels)

POTSDAM, Germany — Want to make robots more trustworthy? The answer may be giving them a familiar accent. Researchers at the University of Potsdam in Germany delved into the way social robots speak to humans and the trust people display in machines after those conversations. The findings show that bots that speak with a local accent appear more trustworthy and competent in the eyes of humans.

Social robots are increasingly becoming part of daily life, assisting in teaching, learning, and caregiving. A key aspect of their design is their ability to interact with humans comfortably. This includes their mode of communication. However, some questions arise: should these robots use a familiar accent or dialect, or should they stick to standard language?

“Surprisingly, people have mixed feelings about robots speaking in a dialect — some like it, while others prefer standard language,” says study lead author Katharina Kühne from the University of Potsdam in a media release. “This made us think: maybe it’s not just the robot, but also the people involved that shape these preferences.”

💡How Do Social Robots Work?

  • Sensory Perception: Social robots have cameras, microphones, and sensors to perceive their surroundings. They “see” through cameras, “hear” through microphones, and “feel” through touch sensors.
  • AI Processing: Using advanced artificial intelligence, the robot processes the sensory data. This AI brain allows it to make decisions and respond to situations.
  • Social Interaction: Based on its understanding, the robot interacts socially with people. It might speak using text-to-speech, display emotions on a screen, or adapt its responses based on your tone and body language.

The study highlights that the trustworthiness and competence of a robot can be influenced by its speech. Standard language is often perceived as more intelligent, but a familiar or friendly dialect can provide comfort.

To investigate these preferences, researchers conducted an online survey with 120 participants from Berlin or Brandenburg. They watched videos of a robot with a male human voice speaking either in standard German or the Berlin dialect, known for its working-class connotations and often used by media to create an informal, friendly impression.

Participants then rated the robot’s trustworthiness and competence and provided demographic information. The survey also recorded the device type used to view the videos. Results showed a correlation between perceived competence and trustworthiness. Generally, the robot speaking standard German was preferable to the participants. However, people who were more familiar with the Berlin dialect favored the robot using the dialect.

“If you’re good at speaking a dialect, you’re more likely to trust a robot that talks the same way,” explains Kühne. “It seems people trust the robot more because they find a similarity.”

laughing teenager with smiling robot
Bots that speak with a local accent appear more trustworthy and competent in the eyes of humans. (© VERTEX SPACE – stock.adobe.com)

Interestingly, participants using mobile devices like phones and tablets, as opposed to computers, gave lower ratings to the robot speaking standard German. Researchers speculate this might be due to distractions and cognitive load from using portable devices, affecting the perceived trust signal of standard German.

“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,” notes Kühne. “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.”

The study also touches on the concept of in-group identity, suggesting that speaking or understanding a dialect can create a sense of similarity and preference for robots that mirror this aspect of identity. However, the prestige associated with a dialect can also influence how it is received by listeners.

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

The study is published in the journal Frontiers in Robotics and AI.

About StudyFinds Staff

StudyFinds sets out to find new research that speaks to mass audiences — without all the scientific jargon. The stories we publish are digestible, summarized versions of research that are intended to inform the reader as well as stir civil, educated debate. StudyFinds Staff articles are AI assisted, but always thoroughly reviewed and edited by a Study Finds staff member. Read our AI Policy for more information.

Our Editorial Process

StudyFinds publishes digestible, agenda-free, transparent research summaries that are intended to inform the reader as well as stir civil, educated debate. We do not agree nor disagree with any of the studies we post, rather, we encourage our readers to debate the veracity of the findings themselves. All articles published on StudyFinds are vetted by our editors prior to publication and include links back to the source or corresponding journal article, if possible.

Our Editorial Team

Steve Fink

Editor-in-Chief

Chris Melore

Editor

Sophia Naughton

Associate Editor

1 Comment

  1. C says:

    Oh please. This article expects us to just “imagine” so many things, without any facts at all or any shred of evidence. This says it all to make it believable “RUDN University in Russia”.