Gendered Words and Grant Rates: A Textual Analysis of Disparate Outcomes in the Patent System

This study examines gender disparities in patent law by analyzing the textual content of patent applications. While prior research has primarily focused on the study of metadata (i.e., filing year or technological class), we employ machine learning and natural language processing techniques to derive latent information from patent texts. In particular, these methods are used to predict inventor gender based on textual characteristics. We find that gender can be identified with notable accuracy - even without knowing the inventor's name. This ability to discern gender through text suggests that anonymized patent examination - often proposed as a solution to mitigate disparities in patent grant rate - may not fully address gender-specific outcomes in securing a patent. Our analysis additionally identifies gendered differences in textual choices within patent documents and the fields in which inventors choose to work. These findings highlight the complex interaction between textual choices, gender, and success in securing a patent. As discussed herein, this raises critical questions about the efficacy of current proposals aimed at achieving gender parity and efficiency in the patent system.