In brief: As Discord’s popularity grows, some communities are becoming too large to moderate manually, and the platform is increasingly becoming an attractive target for cyber-attacks. A new feature released this week helps moderators address these growing issues with automatic keyword filtering.
Discord describes its latest feature, called AutoMod, as a tool to help moderators screen content when there’s too much server traffic to monitor alone, filtering out certain words and phrases. AutoMod will complement, not replace, human mod teams and mod bots.
By default, AutoMod will match text to one of Discord’s multiple preset keyword lists and block messages that contain the usual inappropriate content, such as slander or NSFW material. Discord will update these lists over time, but for now it won’t publish their content so users can’t counter them.
Moderators can also tell AutoMod to catch custom keywords and control what happens to offensive posts. In addition to blocking messages and timing users, the feature can also easily provide automated warnings or advice on the correct spelling of a keyword. For now, non-English servers must set up custom lists because the default keywords are in English only.
Users will inevitably try to get around word filters through alternative spellings. AutoMod’s Wildcards feature tries to stop this by letting moderators scan for keywords within other words. It is also designed to handle words spelled with numbers or other characters.
Moderators can set up AutoMod in Settings > Content Moderation, where they will find the ready-made keyword lists and custom keyword settings. To receive AutoMod alerts, moderators must direct them to a channel, ideally one that only admins and moderators have access to.