Safety options on Koo
Koo stated that the brand new options had been advanced in-house and are in a position to detecting and blocking off any type of nudity or kid sexual abuse fabrics in not up to 5 seconds. Furthermore, they’re going to additionally label incorrect information and conceal poisonous feedback in addition to hate speech at the platform.
“In order to provide users with a wholesome community and meaningful engagement Koo has identified a few areas which have a high impact on user safety,” the corporate stated.
Koo famous that impersonation is without doubt one of the issues on and it’s “actively” running on putting off “their occurrence on the platform”.
Koo’s No Nudity set of rules,
Koo stated that its in-house ‘No Nudity Algorithm’ “instantly” detects and blocks any try by way of a person to add an image or video containing kid sexual abuse fabrics or nudity or sexual content material in “less than 5 seconds.”
Users that put up sexually particular content material will probably be instantly blocked from:
- posting content material
- being came upon by way of different customers
- being featured in trending posts, or
- with the ability to have interaction with different customers in any means
Hiding poisonous feedback
In order to take on poisonous feedback and hate speech, Koo claims its characteristic detects and hides/eliminates such content material in not up to 10 seconds so they don’t seem to be to be had for public viewing.
Warning for violent content material
Koo stated that content material that accommodates over the top blood/gore or acts of violence will probably be overlaid with a caution for customers.
‘MisRep Algorithm’ to take on impersonation
Koo claimed that its in-house ‘MisRep Algorithm’ repeatedly scans the platform for profiles who use the content material or footage or movies or descriptions of well known personalities to stumble on impersonated profiles and block them.
“On detection, the pictures and videos of well known personalities are immediately removed from the profiles and such accounts are flagged for monitoring of bad behavior in the future,” the corporate stated.
‘Misinfo & Disinfo Algorithm’
Koo stated that its ‘Misinfo & Disinfo Algorithm’ scans all viral and reported pretend information in response to private and non-private resources of pretend information, detects them and labels “misinformation and disinformation” on a put up in real-time.
“Our proactive content moderation processes are probably the best in the world!” stated Mayank Bidawatka, Co-founder of Koo.The platform is to be had in additional than 20 languages.