Using genderize.io to infer the gender of first names: how to improve the accuracy of the inference

Authors

  • Paul Sebo

DOI:

https://doi.org/10.5195/jmla.2021.1252

Keywords:

accuracy, gender determination, genderize.io, misclassification, name, name-to-gender, performance

Abstract

Objective: We recently showed that genderize.io is not a sufficiently powerful gender detection tool due to a large number of nonclassifications. In the present study, we aimed to assess whether the accuracy of inference by genderize.io can be improved by manipulating the first names in the database.

Methods: We used a database containing the first names, surnames, and gender of 6,131 physicians practicing in a multicultural country (Switzerland). We uploaded the original CSV file (file #1), the file obtained after removing all diacritic marks, such as accents and cedilla (file #2), and the file obtained after removing all diacritic marks and retaining only the first term of the compound first names (file #3). For each file, we computed three performance metrics: proportion of misclassifications (errorCodedWithoutNA), proportion of nonclassifications (naCoded), and proportion of misclassifications and nonclassifications (errorCoded).

Results: naCoded, which was high for file #1 (16.4%), was reduced after data manipulation (file #2: 11.7%, file #3: 0.4%). As the increase in the number of misclassifications was small, the overall performance of genderize.io (i.e., errorCoded) improved, especially for file #3 (file #1: 17.7%, file #2: 13.0%, and file #3: 2.3%).

Conclusions: A relatively simple manipulation of the data improved the accuracy of gender inference by genderize.io. We recommend using genderize.io only with files that were modified in this way.

References

Sebo P, Clair C. Are female authors under-represented in primary healthcare and general internal medicine journals? Br J Gen Pract. 2021 Jun;71(708):302. DOI: https://doi.org/10.3399/bjgp21x716249.

Cevik M, Haque SA, Manne-Goehler J, Kuppalli K, Sax PE, Majumder MS, Orkin C. Gender disparities in coronavirus disease 2019 clinical trial leadership. Clin Microbiol Infect. 2021 Jul;27(7):1007–10. DOI: https://doi.org/10.1016/j.cmi.2020.12.025.

Gottlieb M, Krzyzaniak SM, Mannix A, Parsons M, Mody S, Kalantari A, Ashraf H, Chan TM. Sex distribution of editorial board members among emergency medicine journals. Ann Emerg Med. 2021 Jan;77(1):117–23.

Gender API [Internet]. Ankara, Turkey: Ozan Soft; c.2018 [cited 2020 Dec 12]. Available from: <https://genderapi.io/>.

Genderize.io [Internet]. Roskilde, Denmark: Demografix ApS. [cited 2020 Dec 12]. Available from: <https://genderize.io/>.

Matias JN. How to ethically and responsibly identify gender in large datasets [Internet]. MediaShift; 2014 [cited 2021 Jan 30]. Available from: <http://mediashift.org/2014/11/how-to-ethically-and-responsibly-identify-gender-in-large-datasets/>.

Peters SAE, Norton R. Sex and gender reporting in global health: new editorial policies. BMJ Glob Health. 2018;3(4):e001038.

Carsenat E. Inferring gender from names in any region, language, or alphabet. [Preprint]. 2019 [cited 2020 Dec 12]. Available from: <http://rgdoi.net/10.13140/RG.2.2.11516.90247>.

Sebo P. Performance of gender detection tools: a comparative study of name-to-gender inference services. J Med Libr Assoc. 2021;109(3):414–21. DOI: dx.doi.org/10.5195/jmla.2021.1185.

Wais K. Gender prediction methods based on first names with genderizeR. The R Journal. 2016 Jan;8(1):17–37. DOI: http://dx.doi.org/10.32614/RJ-2016-002.

Downloads

Additional Files

Published

2021-11-22

Issue

Section

Original Investigation