Koo: Koo launches safety features to block offensive content, misinformation – Times of India

Koo has launched safety features for content moderation on the platform. The indigenous platform said that these features are aimed at offering users a safer and secure social media experience. It also noted that the launch is “an important step towards achieving this goal.”
Safety features on Koo
Koo said that the new features have been developed in-house and are capable of detecting and blocking any form of nudity or child sexual abuse materials in less than 5 seconds. Furthermore, they will also label misinformation and hide toxic comments as well as hate speech on 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 company said.
Koo noted that impersonation is one of the problems on and it is “actively” working on removing “their occurrence on the platform”.

Koo’s ‘No Nudity Algorithm’
Koo said that its in-house ‘No Nudity Algorithm’ “instantaneously” detects and blocks any attempt by a user to upload a picture or video containing child sexual abuse materials or nudity or sexual content in “less than 5 seconds.”
Users that post sexually explicit content will be immediately blocked from:

Hiding toxic comments
In order to tackle toxic comments and hate speech, Koo claims its feature detects and hides/ removes such content in less than 10 seconds so they are not available for public viewing.

Warning for violent content
Koo said that content that contains excessive blood/ gore or acts of violence will be overlaid with a warning for users.
‘MisRep Algorithm’ to tackle impersonation
Koo claimed that its in-house ‘MisRep Algorithm’ constantly scans the platform for profiles who use the content or photos or videos or descriptions of well-known personalities to detect 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 behaviour in the future,” the company said.
‘Misinfo & Disinfo Algorithm’
Koo said that its ‘Misinfo & Disinfo Algorithm’ scans all viral and reported fake news based public and private sources of fake news, detects them and labels “misinformation and disinformation” on a post in real-time.
“Our proactive content moderation processes are probably the best in the world!” said Mayank Bidawatka, Co-founder of Koo. The platform is available in more than 20 languages.