How to Use AutoMod

To improve moderation experience and broadcaster support even further, you can now shield your chat with AutoMod. AutoMod uses machine learning and natural language processing algorithms to hold risky messages from chat so they can be reviewed by a channel moderator before appearing to other viewers in the chat. Moderators can approve or deny any message caught by AutoMod. With AutoMod, broadcasters can establish their own reliable baseline for acceptable language and around-the-clock chat moderation, a way to create a more positive experience for themselves and their communities.

Index (click to jump):


 * How AutoMod Works
 * How to Configure AutoMod
 * Frequently Asked Questions

How AutoMod Works
AutoMod is a moderation tool that blocks inappropriate or harassing chat with powerful moderator control. AutoMod detects misspellings and evasive language automatically.

When a user sends a message that AutoMod flags as potentially inappropriate, the message shown to moderators to be Allowed or Denied. If Allowed, the message will be sent to chat.

Broadcasters can configure AutoMod by selecting one of four levels. These levels affect how aggressively AutoMod holds back messages under four categories: identity, sexual language, aggressive speech, and profanity. These settings can only be changed by the broadcaster, while the dictionary each setting contains is managed by Twitch.

AutoMod does not timeout, ban, or mute users from any channel; it merely withholds comments that fall within the broadcaster's chosen moderation settings to be either approved or denied by the broadcaster's moderators.

Users will receive a notification that their message is being held for review. All users will receive instant feedback that their message is being held for review, as well as a notification if the message was approved or denied. Of course, if approved, the message will instantly appear in chat as the next message.

Broadcasters and their moderators will also still see all the same timeout and ban chatbox options on those messages, so even if the message was denied, there will still be the ability to timeout or ban the user.

How to Configure AutoMod
We recommend you discuss with or inform your moderator team what settings you have used and perhaps which words or phrases you care most about filtering, in order to ensure they adhere to your preferences when they are prompted by AutoMod to review chat messages for approval or denial.

To configure AutoMod:

 * 1) Go to your Dashboard page and select “Moderation” from the left-side menu underneath the Settings header.
 * 2) Click on the Choose level button.
 * 3) You will be defaulted to Level 1, the second lowest moderation setting. Drag the slider bar to choose the setting most appropriate for you, from Level 0 to Level 4 (the strongest default setting). If you prefer to create a custom level, you may update each moderation category individually.
 * 4) You may also go to your Channel Settings page and review the other settings in the Chat Options section to ensure everything is set up or updated to work best for your community.

You can choose one of five levels for your AutoMod setting. Each level catches all words from the previous level, plus more. The higher the level, the more AutoMod will catch. You can see how strictly AutoMod will filter based on how many shields are displayed in each moderation category, from zero (no moderation) to four (a lot of moderation). You can also create a custom level by updating each moderation category individually.

AutoMod moderation categories:

 * Identity language - Words referring to race, religion, gender, orientation, disability, or similar. Hate speech falls under this category.
 * Sexually explicit language - Words or phrases referring to sexual acts, sexual content, and body parts.
 * Aggressive language - Hostility towards other people, often associated with bullying.
 * Profanity - Expletives, curse words, and vulgarity. This filter especially helps those who wish to keep their community family-friendly.

What AutoMod catches at each level:

 * Level 0: Only commonly blocked terms.
 * Level 1: Only remove hate speech.
 * Level 2: Also remove sexually explicit language and abusive language.
 * Level 3: Remove even more identity language and sex words.
 * Level 4: All of the above, plus profanity and mild trash talk.

Please note: Hate speech, bullying, and sexually explicit content is not allowed under Twitch’s community guidelines. If you see it, please report it.

How channel moderators can update AutoMod
Your channel’s moderators can also access and update AutoMod settings by selecting “Manage Moderation Settings” from the chat settings menu. That option opens the moderation settings page in your broadcaster dashboard, where they can update your AutoMod level, create a custom level, and update terms in your blocked and permitted terms list.

Note: If you have a blocked term that you prefer your mods not see, you may set it as private. Private blocked terms are only visible to you.

Frequently Asked Questions

 * Q. What languages is AutoMod available in?
 * A. AutoMod is available in: English, German, Spanish, Spanish (Mexico), French, Italian, Japanese, Korean, Dutch, Polish, Portuguese (Portugal), Portuguese (Brazil), Russian, Slovak, Turkish, Chinese (PRC) and Chinese (Taiwan).
 * Q. How will AutoMod operate as new meanings and slang words grow on the internet so frequently?
 * A. Twitch will be regularly reviewing how moderators use AutoMod to maintain its effectiveness on a site-wide and per channel basis. The feedback from your moderators approving and denying messages, as well as removing other messages not caught by AutoMod, will help to grow our understanding of how language used on Twitch evolves. Our goal is for a broadcaster's chosen AutoMod setting to reflect how they want to run their chat.
 * Q. What if I want to customize my AutoMod settings even further, like with a whitelist or blacklist for words the settings I have chosen do not include?
 * A. We now support blocked and permitted terms. Each term can be more than one word, and automod will also try to fix misspellings or evasive language when checking a message.
 * Q. Can my moderators update AutoMod?
 * A. Yes, moderators can update your AutoMod level, create a custom level by fine-tuning each moderation category, and update terms in your blocked and permitted terms lists. To access AutoMod settings in the broadcaster dashboard, mods can click “Manage Moderation Settings” in the chat settings menu.
 * Q. Can moderators see all my blocked terms?
 * A. No, if a blocked term is marked as private, it is only visible to you. Mods are able to see and update blocked terms that are not marked as private.
 * Q. What other tools and options are there to ensure a quality chat experience for viewers? In addition, broadcasters can assign members from their own community to moderate their chats, use Mod Logs 1.1 for tracking moderator actions, add a non-moderator chat delay of anywhere from 2-6 seconds to allow more time for their moderators to manage messages, and employ a recent Chat Rules option which requires viewers to agree to the channel rules set forth from the streamer before they can chat.
 * A. AutoMod joins a number of moderation tools including: enabling broadcasters to ban links, specific words, repeated phrases, and ban individuals from chat, as well as the ability to slow chat down, make it emote only, or make it so only users subscribed to the channel (if it is Partnered) and the channel’s moderators can participate in chat.