Koo introduces new security options for content material moderation

Koo, an Indian microblogging platform, has unveiled new proactive content material moderation options geared toward enhancing consumer security and safety on social media. The platform claims that its in-house developed options can detect and block any cases of nudity or baby sexual abuse supplies proactively inside 5 seconds. Moreover, the platform can label misinformation, disguise poisonous feedback, and stop hate speech from being printed on the platform.

As per Koo, the microblogging platform has launched new content material moderation options that purpose to reinforce the protection and safety of customers whereas utilizing social media. The platform’s in-house developed options can detect and block nudity and baby sexual abuse supplies in lower than 5 seconds, label misinformation, and conceal poisonous feedback and hate speech. 

Listed below are particulars on Koo’s security options:

Nudity: Koo’s in-house “No Nudity Algorithm” is designed to proactively detect and immediately block any try by a consumer to add footage or movies containing baby sexual abuse supplies, nudity, or sexual content material, as per the corporate. Koo says that the algorithm can detect and block such content material in lower than 5 seconds. When a consumer posts sexually specific content material, they’re instantly prevented from posting content material, being found by different customers, being featured in trending posts, or partaking with different customers on the platform.

Poisonous Feedback and Hate Speech: In accordance with Koo, its in-house expertise proactively detects and removes poisonous feedback and hate speech in lower than 10 seconds to make sure they don’t seem to be seen to the general public.

Violence: Customers are supplied with a warning overlay for content material that accommodates extreme blood, gore, or acts of violence. 

Impersonation: Koo employs an in-house algorithm referred to as ‘MisRep Algorithm’ to recurrently scan its platform for profiles that use content material, photographs, movies, or descriptions of well-known people in an try to impersonate them. When detected, the algorithm swiftly removes any footage or movies of the well-known people from the profiles and flags the accounts for future monitoring of potential improper conduct.

Misinformation and Disinformation: The corporate revealed that it developed an in-house algorithm referred to as the ‘Misinfo and Disinfo Algorithm,’ which constantly and immediately scans all viral and reported faux information on the platform utilizing each private and non-private sources of pretend information. The algorithm identifies and labels misinformation and disinformation current in a publish, successfully decreasing the dissemination of viral false info on the platform.


Catch all of the Expertise Information and Updates on Reside Mint.
Obtain The Mint Information App to get Every day Market Updates & Reside Enterprise Information.

Much less

Supply By https://www.livemint.com/expertise/apps/koo-introduces-new-safety-features-for-content-moderation-11679567037371.html

Related posts