What's in a Name? -- Gender Classification of Names with Character Based Machine Learning Models
This work provides a solution for tech companies and researchers to infer user gender from names, which is important for identifying and intervening in gender bias within recommender systems, especially for users who opt not to provide this information.
This paper addresses the problem of inferring user gender from names, crucial for mitigating bias in recommender systems when explicit gender data is unavailable. By analyzing over 100 million user names, the authors developed character-based machine learning models that significantly outperform baseline models in gender classification, with further improvements when incorporating last names.
Gender information is no longer a mandatory input when registering for an account at many leading Internet companies. However, prediction of demographic information such as gender and age remains an important task, especially in intervention of unintentional gender/age bias in recommender systems. Therefore it is necessary to infer the gender of those users who did not to provide this information during registration. We consider the problem of predicting the gender of registered users based on their declared name. By analyzing the first names of 100M+ users, we found that genders can be very effectively classified using the composition of the name strings. We propose a number of character based machine learning models, and demonstrate that our models are able to infer the gender of users with much higher accuracy than baseline models. Moreover, we show that using the last names in addition to the first names improves classification performance further.