All About the Name: Assigning Demographically Appropriate Names to Data-Driven Entities

We develop a method for assigning demographically appropriate names to data-driven entities, such as personas, chatbots, and virtual agents. The value of this is removing the time-consuming human effort in task. To demonstrate our method, we collect four million user profiles with gender, age, country information from an international online social network. From dataset, obtain 1, 031, 667 unique covering 3, 088 demographic group combinations that considers nationality appropriate. A manual evaluation by raters 34 countries shows appropriateness score 85.6%. can be utilized agents, other humanized entities.