This page explores our metadata, in other words, the categorization of the faces.
From our larger dataset (consisting of 327,322 faces extracted from 3,389 issues), we drew a subset of 8,789 faces from a sample of 100 issues, which we categorized by detailed characteristics including gender, facial expression, age, race, and context. The data charted over time revealed several large-scale trends that are consistent with the historical context of the magazine, as discussed in our research findings.
Conditions and context influence which faces are presented, and how each face therein is represented. Categorizing the faces and charting the features over time can reveal a bigger picture of trends in our own cultural history.
The button below will reveal options of features that you can chart and explore. What conclusions can you draw from the data?
Other Face Features