Maintaining a respectful and positive environment is key to the success of any online community. Keep your community safe by ensuring no offensive messages are sent in your chatrooms! Returning.AI’s content moderation provides the tools you need to manage your chatrooms effectively, creating a space where members feel comfortable engaging, discussing, and sharing, fostering a stronger, healthier community.

Returning.AI's content moderation is split into three parts, each with a specific purpose in your community:

Profanity Filter: This feature blocks messages containing offensive words and provides warnings to users attempting to use inappropriate language.

Banned Words: This feature prevents users from sending messages with specific banned words and issues warnings when these words are used.

Alert Words: Monitors the use of specific words and sends alerts to selected channels whenever these words are detected.

To set up your Profanity Filter, head into your Content Moderation settings and toggle it on. Returning.AI has compiled a list of default profanities that will be flagged by the profanity filter. You can view and edit this list by clicking on "Edit Default List." In the pop-up window, click on "Show List" to see all the profanities that are currently being monitored.

If you want to allow certain words from the default list, enter them in the "Exclude Profanities from List" box. This ensures those words are permitted in your community. To add extra words to the filter, type them into the "Add Profanities to List" box. This will update your filter to catch and manage these new words.

Once you've edited your profanity list, enter a custom warning message that will be shown to any community members who attempt to send offensive words to your channels. This will ensure that users are informed about the content guidelines and the consequences of using inappropriate language.

Once you're finished, click "Save" to apply your changes.

To set up your banned words, simply enter the words or phrases you want to block from being sent to your community. This list is separate from your profanity filter, allowing you to target more specific or industry-related terms.

The warning message shown to members when they try to send a banned word will also be distinct from the one used for profanities.

To set up alert words, enter the words or phrases you want to monitor. Then, select a channel to receive alerts whenever these words are detected in your community. It's best to choose a private channel accessible only to community owners and administrators, ensuring that alert logs remain private.

Once you've chosen your alert channel, save your changes.