"Ick bin een Berlina": dialect proficiency impacts a robot's trustworthiness and competence evaluation

Area of Science:

• Human-Robot Interaction
• Sociolinguistics
• Artificial Intelligence

Background:

• Social robots are increasingly interacting with humans, featuring various voices and accents.
• Research on user preference for robot dialects is mixed, with some favoring user dialects and others preferring different ones.
• Understanding dialect's impact on robot perception is crucial for effective human-robot interaction.

Purpose of the Study:

• To investigate how the Berlin dialect affects perceptions of a social robot's trustworthiness and competence.
• To explore the relationship between users' dialect proficiency and their assessment of robot characteristics.
• To identify demographic factors influencing the perception of dialect-speaking robots.

Main Methods:

• 120 German native speakers evaluated a NAO robot in a video.
• The robot spoke either in the Berlin dialect or standard German.
• Participants rated the robot's trustworthiness and competence, with dialect proficiency and demographic data collected.

Main Results:

• A positive correlation was found between participants' Berlin dialect proficiency and their perception of the dialect-speaking robot's trustworthiness.
• Robot competence positively predicted its trustworthiness.
• Demographic factors like age, gender, and residency influenced robot assessments, with dialect proficiency also affecting competence ratings for the standard German robot.

Conclusions:

• Dialect plays a significant role in shaping user perceptions of social robot trustworthiness and competence.
• Individual dialect proficiency and performance can influence how users evaluate robot characteristics.
• Future research should consider demographic variables and device control in online human-robot interaction studies.