GenPORT is funded by the European Union FP7-SCIENCE-IN-SOCIETY-2012-1 programme.

NamSor Gender API

Submitted by namsor on Wed, 05/28/2014 - 13:47
About (original language)

NamSor™ is a European designer of name recognition software. Our mission is to help make sense of the Big Data and understand international flows of money, ideas and people.

Our specialized data mining software recognizes the linguistic or cultural origin of personal names in any alphabet / language, with fine grain and high accuracy. Names are meaningful : we use sociolinguistics to extract their semantics and deliver actionable intelligence.

We apply this innovative technology to support our clients in their development : countries, regions, private companies, projects, in all sectors of activity.

 

Based on the software, GendRE API is a public accessible interface to predict the gender of a name  on a scale from -1 to 1 for a given geography/locale. This allows for gender (im-)balance monitoring based on data analysis such as the Gender Gap in the Film Industry.

The REST API is free to use and available under: http://namesorts.com/api/

 

 

About (English version)

NamSor Gender API is quite unique in the way we combine the first name and the last name together, to recognize the likely cultural origin and gender at the same time, for higher precision and recall.

Global coverage : NamSor covers all languages, alphabets, countries, regions. We constantly improve the precision, working with linguists, anthropologist and historians. We can recognize, for example, the gender of Indian names in scripts such as TELUGU, ORIYA, GURMUKHI, MALAYALAM, BENGALI, GUJARATI, KANNADA, DEVANAGARI, TAMIL, ARABIC, LATIN. 

The Gender API is free to use for individual calls, but if you register, you will get additional benefits such as: higher throughput (to genderize thousands of names per second), integration with data mining tools, a simple web access to process Excel or text files.

We also provide other name APIs, NamSor Origin and NamSor Diaspora to infer the likely nationality or ethnicity/diaspora of social groups, based on personal names.

On GitHub,

 

Public identifier
namsor.com
Type of resource
Media Type
Geographic provenance
Date created
Updated periodically?
Approx. every half year
Is this resource freely shareable?
Shareable
Scientific discipline
Country coverage
Copyleft license
GPL
Intended target sector