What’s the Gender Gap in the European Union Whoiswho?

Posted by

This summer, the European Union has published an updated version of The Official Directory of the European Union [mirror: FYWW13001ENC.pdf, in ZIP/Excel format TheEUDirectory_xls.zip].

The EU Directory is not a good candidate for the GenderGapGrader initiative – because it’s not a truly global database like the FAA Airman Directory or the Internet Movie Database (IMDB), which we’ve used to disclose the gender gap among airline pilots or in the film industry.

But it’s a useful document, which lists people from all countries of Europe with their title (Mr, Ms). We can use it to validate our methodology, specifically compute the error rate of the software we use to predict the gender of names. The document lists about fifteen thousand EU executives, with different roles : Member, Head of Unit, Substitute, Director, Counsellor, Head of Division, Legal secretary, Vice-Chair, Attaché, First Secretary, Member of the Bureau, Administrator, Adviser, Head of Delegation, Second Secretary, Acting Head of Unit, Vice-President, Head of Service, Chair, Head of Office, Director-General, Delegate, Head of Sector, Assistant to the Director-General, Bureau member, Third Secretary, Judge, Head of private office, Acting Director, Head of Cabinet …

We’ve used RapidMiner with the Onomastics extension (available free in RapidMiner MarketPlace) to calculate the Gender Gap, then we’ve compared the results from then actual counts using titles (Mr, Ms). The software recognizes the origin of personal names to solve cases such as Andrea Rossini (likely Male) or Andrea Parker (likely Female), Jean, Kim etc. The use of the ‘gender scale’ metric (a numeric value between -1 and +1), instead of the predicted gender (Male, Female or Unknown), helps level cases of truly genderless names such as Kerry.


20140905_TheEUDirectory_GenderGap_scale_cc_vF

In the chart above, the difference cannot be seen with the human eye: onomastics are a reliable tool to measure the gender gap. In most cultures, names can be used to accurately predict gender (with the notable exception of Chinese names, Korean names once transliterated).

The European Institute for Gender Equality is an EU agency based in Vilnius, Lithuania, which promotes gender equality, fights discrimination based on sex and raises gender awareness. What about promoting gender equality among EU political institutions;-) We believe such new data mining capabilities and growing open data initiatives can help public and private organisations find innovative solutions to close the gender gap.

20140905_Genderizing_TheEUDirectory_using_RapidMiner
Using RapidMiner Onomastics extension to measure the Gender Gap

Additional information in the EU Directory allows to visualize other factors affecting the gender gap : EU Country of affiliation, role, …

20140905_TheEUDirectory_GenderGap_a_vF

20140905_TheEUDirectory_GenderGap_b_vF

We are continuously improving the software to predict the origin and gender of names. The coming version of GendRE API v0.0.16 will still enhance the accuracy. Also, please stay tuned for the upcoming GenderGapGrader study on women entrepreneurship, start-ups and access to financing (VCs, Business Angels…)

To redo this study or make your own

– Get the source data files used in this article [mirror: FYWW13001ENC.pdf, in ZIP/Excel format TheEUDirectory_xls.zip]

– Get RapidMiner with Onomastics extension and Documentation, watch the tutorial video

– Or download directly the results TheEuropeanUnionDirectory_genderized.zip

About NamSor

NamSor™ Applied Onomastics is a European designer of name recognition software. NamSor is committed to promote diversity and equal opportunity. NamSor launched GendRE API, a free API to extract gender from personal names. We support the @GenderGapGrader initiative. http://namsor.com

About GenderGapGrader

GenderGapGrader’s mission is to publish gender gap estimates at the finest grain level, using whatever reference database we can identify for a particular industry: The Internet Movie Database (IMDB) for the film industry, “The Airman Database” for pilots… and more to come. http://gendergapgrader.com

Creative Commons License
‘What’s the Gender Gap in the European Union Whoiswho?’ by gendergapgrader is licensed under a Creative Commons Attribution 4.0 International License. Based on a work at http://namesorts.com/2014/09/09/whats-the-gender-gap-in-the-european-union-whoiswho/.

Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s