Tech News Desk – India’s microblogging platform Koo has announced the launch of a new active moderation feature designed to provide users a safe and secure social media experience. The in-house developed feature is capable of proactively detecting and blocking any type of nudity or child sexual abuse content, labeling misinformation and hiding cross-platform comments and hate speech in less than 5 seconds. The company is continuously working to remove such content from the platform.
nudity
Kuo’s in-house ‘No Nudity Algorithm’ actively and immediately detects and blocks any attempt by a user to upload child sexual abuse material or a photo or video containing nudity or sexual content. It takes less than 5 seconds to detect and block.
foul language
Proactively detects and hides or removes offensive comments and hate speech in less than 10 seconds so that they are not available for public viewing.
violence
Content containing excessive blood/gore or violence is overlaid with a warning to the user.
MisRep algorithm features
Kuo’s in-house ‘MisRep algorithm’ constantly scans the platform and blocks profiles that use content or photos or videos or details of celebrities. The company claims that photos and videos of well-known personalities are immediately removed from profiles when they are detected and such accounts are flagged to monitor bad behavior in the future.
use of false information
Koo’s in-house ‘Misinfo & Disinfo algorithm’ proactively and in real-time scans all viral and reported fake news based on public and private sources to detect misinformation on any given post and can be labelled.