When collecting user-generated content for a certain hashtag, spam and abusive content can sometimes be an issue. Walls.io has got you covered with our automatic AI Content filters!
You will find these filters under Moderation > Filters.
Text Spam Filter
The first filter, available to all plans, analyzes the text of a caption. It takes a look at hashtags, keywords, and text that may be harmful or inappropriate and automatically blocks them from appearing on your wall.
You can choose between Default and Strict mode. While Default will hide all posts that are certainly spam, Strict mode will go a bit further and also hide posts that are only very likely to be spam.
A description about each of the sensitivity levels will be displayed below the slider.
AI Image Filter
This filter, available to enterprise customers only, uses image classification techniques to detect unwanted content in an image according to nine spam categories. The filter understands what’s in an image, not just the caption, and stops unsafe visuals from appearing on the screen.
The nine categories are as follows:
Nudity
Porn
Sexualized
Hate
Abuse
Self-harm
Violence
Illegal
Extremism
Select the categories you would like to use for image detection by clicking on the dropdown labelled 1. You can remove categories by clicking the X by its name.
Based on how a post meets these filters' criteria, the post will either become visible or hidden automatically. If the AI is unsure about the image or text, it will send it to the Needs Review tab.
There, you'll be able to Show, Hide, or Delete the post.
In case you have further questions, don't hesitate to contact the support team via the chat or support@walls.io!





