The study, which was conducted by researchers at MIT, looked at the reactions of family members to the voice-user interfaces.
The researchers found that family members were more likely to find a device to be competent and emotionally engaging if it can exhibit social cues, such as moving to orient its gaze at a speaking person.
When a device had higher levels of social embodiment, “such as the ability to give verbal and non-verbal social cues through motion or expression, family members also interacted with one another more frequently while engaging with the device as a group,” the researchers noted.
The study also revealed that the brand of a voice-user interface also had a significant effect on how it was viewed.
According to MIT, the results could help the makers of voice-user interfaces create devices that are more engaging for consumers. However, the researchers pointed to ethical concerns that could arise “from certain personality and embodiment designs.”
For the study the researchers designed three experiments that involved family members interacting as a group with different voice-user interfaces.
In total, 34 families, comprising 92 people between age 4 and 69, participated in the studies. The experiments were designed to mimic a family’s first encounter with a voice-user interface.
The families who took part in the study were filmed as they interacted with three devices - Jibo robot, Amazon Echo and Google Home.
The families were asked to undertake a list of 24 actions, such as asking the device about the weather. Then they answered questions about their perception of the devices and categorized the voice-user interfaces’ personalities.
According to the researchers, majority of the family members surveyed found the Jibo to be the most outgoing, dependable, and sympathetic of the three devices. The researchers attributed this choice to the fact that the users perceived that Jibo had a more human-like personality.
“These devices are new technology coming into the home and they are still very under-explored,” said Anastasia Ostrowski, a research assistant in the Personal Robotics Group in the Media Lab, and lead author of the paper.
“Families are in the home, so we were very interested in looking at this from a generational approach, including children and grandparents. It was super interesting for us to understand how people are perceiving these, and how families interact with these devices together.”
The second experiment looked at the impact branding had on perception. For this experiment they changed the ‘wake word’ (the word the user speaks aloud to engage the device) to incorporate the name of the brand, meaning that the users had to say, “Hey, Amazon!” to awaken the Amazon Echo.
When this was done they discovered that users perception of the Amazon Echo in particular was negatively effected.
“I was not expecting it to have that big of a difference between the first and second study. We didn’t change any of the abilities, how they function, or how they respond,” said Ostrowski. “Just the fact that they were aware the device is made by Amazon made a huge difference in their perceptions.”
In the third experiment, the team wanted to see how interpersonal movement affected the interactions. They looked at the effect of the Jibo robot turning its gaze to the individual who was speaking, for example.
This mimicking of human-like social behaviors not only led to the family members engaging more with the device, the researchers also noted them interacting more among themselves, like glancing at each other or laughing together.
“In the home, we have been wondering how these systems promote engagement between users. That is always a big concern for people: How are these devices going to shape people’s relationships? We want to design systems that can promote a more flourishing relationship between people,” said Ostrowski.