“We have built sophisticated machine learning systems to detect abusive behavior and ban suspicious accounts at registration, during messaging, and in response to user reports We remove over two million accounts per month for bulk or automated behavior – over 75% without a recent user report,” wrote the company.
Facebook-owned WhatsApp, like its parent company, has been under much flak for being a platform where misinformation is spread.
The trend was at such high that phrases like ‘WhatsApp universities’ denoting reliance on misinformation propagated through the instant-messaging app, were a part of political discourse and campaigns, mostly by the left-leaning Indian National Congress.
Ahead of the Indian general elections, WhatsApp had placed several in-app restrictions to stop users from sharing bulk messages containing misleading information.
“We use labels to mark the worst offenders and distinguish between their behaviors from those of regular users. We use the features and labels to teach our systems to better predict whether a user is likely to be banned in the future,” said WhatsApp.