Online platforms take different approaches to moderating — or not — the content that can be published or discovered through their platforms. I discovered today that some of the GIF search engines are censoring certain search terms. So I decided to poke a little more and see what is happening.
When you search for ‘nazi’ on Giphy, you get this:
In WhatsApp's gif search, powered by Tenor, you see:
It seems, though, that this filter is implemented by WhatsApp. Tenor's web site will happily return Nazi GIFs. No, I'm not going to provide a screenshot.
Curiosity killed the frog, so I went farther. What do these search engines do with ‘pepe’, the green frog mascot of certain corners of the alt-right?
Giphy doesn't like the frog, but instead of no results, it return results related to soccer and a skunk I don't recognize:
Neither WhatsApp nor Tenor do this filtering, though - a search for ‘pepe’ returns a plethora of images of the frog.
Interestingly, it looks like Giphy is employing image recognition for this filter instead of relying solely on tags to keep Pepe away. When I search for ‘frog’, I find a number of frogs, including everyone's favorite green frog, but no Pepe in the first several screens:
A Tenor search for ‘frog’ includes Pepe:
It looks to me like Giphy has made the decision that they do not want to be a source of GIFs for alt-right and neo-Nazi communication, and invested nontrivial effort to avoid it as evidenced by the fact that it appears their curation and filtering goes beyond keyword matching. I expect this has minimal impact on actual online communication — people who want to spread Pepe gifs will find them — but it removes one source of media resources & reduces the likelihood of Giphy being linked to such communication.
Tenor has not made this decision. WhatsApp is unclear: they may simply be deploying efforts to be compliant with German and French laws against dissemination of Nazi imagery worldwide. Twitter's GIF search seems to work the same as WhatsApp.