Replication Data for: Inferring Gender from First Names: Comparing the Accuracy of Genderize, Gender API, and the gender R Package on Authors of Diverse Nationality

This dataset includes four files relevant to the submitted manuscript: Inferring Gender from First Names: Comparing the Accuracy of Genderize, Gender API, and the gender R Package on Authors of Diverse Nationality. The file ‘minimal_data_set_field_definitions.docx’ defines the columns in the three included tables. All tables include the gender predictions from tools that infer gender from first names. The table ‘minimal_data_set_hemonc.csv’ includes the first names of clinical trialists from the HemOnc knowledgebase. The table ‘sebo_minimal_data_set.csv’ includes a table of names that were originally analyzed by another research group (http://jmla.pitt.edu/ojs/jmla/article/view/1185, https://osf.io/kr2mx/). Lastly, the table ‘santamaria_minimal_data_set.csv’ includes a different set of names that were originally featured in a different study (10.7717/peerj-cs.156, https://github.com/GenderGapSTEM-PublicationAnalysis/name_gender_inference).