The Gender Equality Tech Tool (GETT) involves the collection, analysis, and visualization of data on the visibility of women, including female scientists. The data analysis draws on texts from public reporting by universities, research institutions, as well as traditional and digital media (e.g., news articles, announcements, interviews, reader comments, and discussions). This data is regularly and automatically collected via APIs or provided directly by German media houses collaborating within the framework of this project. The present analysis incorporates data from three  major media houses.

For the stereotype analysis, descriptive and occupational texts referring to a person in an article are examined using natural language processing (NLP) methods and semantic similarity analyses. The analysis is currently in the pilot phase. A detailed description of the methods used can be found here.

BMBF LogoLogo Metavorhaben IfifTUM Logo

JOIN OUR COMMUNITY

The GETT is available free of charge to editorial offices and research institutions. We are still looking for cooperation partners! We will analyse your data free of charge and easily — write to us without obligation.

Get in touch →

FAQs

Which technical methods were used for data analysis?

Plus icon

For data analysis, we use a combination of classic algorithms and open-source AI models. You can find further details in our GitHub repository.

How were the proportions of men and women calculated in the articles analysed?

Plus icon

All names of female and male persons were taken into account for the calculation. The relative share is calculated by dividing the absolute number of mentions by women and men by the total number of all mentions.

How was the data collected?

Plus icon

The data for the Gender Equality Tech Tool (GETT) comes from public reports from universities, research institutions and media. These are regularly collected automatically via APIs or provided by media partners, which also include paid offers.