"Sexually Suggestive Content featuring Minors (SSCM) is 2-3x higher on Reels than Explore"

"Ranking models cause integrity regressions by increasing the prevalence of non-recommendable content. Increasing topic diversity increased all objectionable content, and recommending based on P(click), Mimicry, and downranking watermarked media increased the prevalence of sexually suggestive content." "Trends, Entertainment, and Mimicry can lead to harm. Risky trends (i.e., the TikTok WAP trend for teens or trends mocking disabilities) may leave people open to harm, ranging from seeing harmful content to bullying or predatory behaviors. Offensive content (hate speech, violence, bullying) may also be delivered under the guise of 'entertainment' at higher rates on Reels." "Unconnected dancing videos featuring young girls raise safety concerns. Studies and internal feedback suggests that people are uncomfortable with seeing and concerned about the safety of unconnected Reels content of tween and young girls dancing and posing." "Sexually Suggestive Content featuring Minors (SSCM) is 2-3x higher on Reels than Explore*. Female and unknown gender teens, as well as unknown gender non-teens, create the most SSCM. However, we're also over-enforcing by labeling birth announcements and parenting videos under this category. (DM me for quip on Protecting Youth!)" "The highest perceived reach integrity types are the least detected, and vice versa. People didn't often report the highest labeled prevalence integrity types (sexually suggestive, violence, graphic content). Similarly, hate speech and bullying are some of the lowest detected prevalence on Reels, but participants reported witnessing those more often and report them as being more upsetting." "Female and 'Unknown Gender' Teens create 73% of 'SSCM' content created by teens... ...While male teens report the most. 'Custom Gender' Teens both create (1.2%) and report (1.9%) 'SSCM' content at higher rates than their DAU (.4%)." "Benign but still risky content featuring minors: Children dancing/posing unto itself is not problematic, but it becomes an issue if bad actors see it. Tolerance for this content varies by country and is not preferred for many non-teen users. Preventing IICIICInappropriate Interactions with ChildrenA classifier threshold and content category for interactions between adults and children indicative of grooming or exploitation, referred to internally as "a.k.a. 'grooming'". The source document puts the scale at "~500k victims per DAY in English markets only", three times Messenger's prevalence, while calling it "a preliminary metric" and adding "we expect the true situation is worse".Full entry ↗ actors from seeing/interacting with minors, more effective / child content personalization (SFPLT) or creating 'teen-centered' ranking approaches for teens may help solve this problem."