Performance of gender detection tools: a comparative study of name-to-gender inference services

Objective: To evaluate the performance of gender detection tools that allow the uploading of files (e.g., Excel or CSV files) containing first names, are usable by researchers without advanced computer skills, and are at least partially free of charge.Methods: The study was conducted using four physician datasets (total number of physicians: 6,131; 50.3% female) from Switzerland, a multilingual country. Four gender detection tools met the inclusion criteria: three partially free (Gender API, NamSor, and genderize.io) and one completely free (Wiki-Gendersort). For each tool, we recorded the number of correct classifications (i.e., correct gender assigned to a name), misclassifications (i.e., wrong gender assigned to a name), and nonclassifications (i.e., no gender assigned). We computed three metrics: the proportion of misclassifications excluding nonclassifications (errorCodedWithoutNA), the proportion of nonclassifications (naCoded), and the proportion of misclassifications and nonclassifications (errorCoded).Results: The proportion of misclassifications was low for all four gender detection tools (errorCodedWithoutNA between 1.5 and 2.2%). By contrast, the proportion of unrecognized names (naCoded) varied: 0% for NamSor, 0.3% for Gender API, 4.5% for Wiki-Gendersort, and 16.4% for genderize.io. Using errorCoded, which penalizes both types of error equally, we obtained the following results: Gender API 1.8%, NamSor 2.0%, Wiki-Gendersort 6.6%, and genderize.io 17.7%.Conclusions: Gender API and NamSor were the most accurate tools. Genderize.io led to a high number of nonclassifications. Wiki-Gendersort may be a good compromise for researchers wishing to use a completely free tool. Other studies would be useful to evaluate the performance of these tools in other populations (e.g., Asian).

American as Apple Pie

This brief tribute to Carolee Schneemann examines her self-conception as an American artist, considering how it intersects with the disruptive performance of gender norms in Americana I Ching Apple Pie (1972). The work was originally staged for the camera in Schneemann's London kitchen in 1972, during a period in which the artist was living in voluntary exile. She published a performance score for the piece in her artist's book Parts of a Body House (1972) and reprinted it in Cezanne She Was a Great Painter (1974–75). This essay reads Americana I Ching Apple Pie as an unruly reenactment of the highly gendered role that the filmmaker Stan Brakhage cast Schneemann to play in his short experimental film Cat's Cradle (1959). It considers the way she understood home and homeland as two interlocking fronts in the ongoing battle over how gender is encoded and enacted. It concludes by briefly considering the reception of Schneemann's work by a younger generation of artists, including Sondra Perry, who staged an homage to Americana I Ching Apple Pie in 2015.

‘La herida de un hombre no es una novedad’: Gender, violence and performance in Azul y no tan rosa

Azul y no tan rosa was the first Venezuelan film to win the Goya for Best Spanish Language Foreign Film. It was also the first Venezuelan film to feature a kiss between two men, as well as an openly transgender character. At the heart of the film is a scene which cross-cuts between transsexual Delirio performing the 1980s Venezuelan pop hit ‘No soy una señora’ and a vicious homophobic attack. This scene exemplifies the film’s preoccupation with the performance of gender, its denunciation of machista violence, and its call for acceptance of difference.

Gender prediction via deep learning across different retinal fundus photograph fields: a multi-ethnic study (Preprint)

BACKGROUND Deep Learning (DL) algorithms have been built for detection of systemic and eye diseases from retinal photographs. The retina possesses features which can be affected by gender differences, and the extent to which these features are captured upon photography differs depending on the retinal image field. OBJECTIVE To compare DL algorithms’ performance in predicting gender when using different fields of retinal photographs (disc-centered, macula-centered, peripheral). METHODS This retrospective cross-sectional study included 172,170 retinal photographs from 9956 adults aged ≥ 40 years from the Singapore Epidemiology of Eye Diseases (SEED) Study. Optic disc-centered, macula-centered and peripheral field retinal fundus images were included in this study as input to a DL model for gender prediction. Performance was estimated at individual level and image level. Receiver operating characteristic (ROC) curves for binary classification were calculated. RESULTS The DL algorithms predicted gender with area under the ROC (AUC) of 0.94 at individual-level and AUC of 0.87 at image-level. Across the three image fields, the best performance was seen in disc-centered (AUC: 0.91 in younger and 0.86 in older age subgroups), and peripheral field images showed the lowest performance (AUC: 0.85 in younger and 0.76 in older subgroups). Between the three ethnic subgroups, performance was lowest in the Indian subgroup (AUC: 0.88) compared to Malay (AUC: 0.91) and Chinese (AUC: 0.91) when tested on disc-centered images. The performance of gender prediction at the image level was better in younger age subgroups of < 65 years (AUC: 0.89) than in older age subgroups of ≥ 65 years (AUC: 0.82). CONCLUSIONS We confirmed that gender can be predicted from retinal photographs using DL in Asian population, and the performance of gender prediction differ according to field of retinal photographs, age-subgroups, and ethnic groups. Our work provides a further understanding of using DL models for prediction of gender-related diseases. Further validation of our findings is still needed.

Performing Gender, Performing Documentary in Postsocialist China

This chapter focuses on Tang Tang (Zhang Hanzi, 2004) and Mei Mei (Gao Tian, 2005), two Chinese documentaries. Although each documentary centers around a female impersonator, they approach their subjects in distinct ways. While Mei Mei portrays its subject with nuance and intense emotional investment, Tang Tang emphasizes formal experimentation. Positioning Tang Tang at the intersection of what I call the film’s “performing documentary” and the subject’s “performance of gender,” I argue that the reflexivity permeating Tang Tang foregrounds the openness of the queer subjectivities it portrays. My investigation further addresses each film’s subjects as human beings materialized in and through a matrix of social, political, and economic conditions marked by spatial and temporal parameters.