The virtual world of multimedia messaging apps has taken hold as the primary medium of our daily conversation, creating a lot of scope for spam, bulk, and automated messages. Set in this scenario, one of the most popular messaging/chat apps, WhatsApp released new white-paper containing the specifics of how the company fights spam, bulk, and automated messages. As per the company, about 90% of the messages sent on WhatsApp are from one person to another, and most of the groups have less than 10 people. This announcement follows the Safe Internet Day on February 5, propping up the safe use of internet messaging apps in effect.
The app abuse detection technology of WhatsApp has 3 stages, registration, during messaging and in case of negative feedback and out of its 1.5 billion users, it has already banned 6 million accounts over 3 months on account of either of these 3 stages. The first stage i.e. the registration is compulsory for all the potential users and its sophisticated machine learning systems detect abusive behavior and ban suspicious accounts at registration, during messaging, and in response to user reports, which makes for an impressive weeding-out-spam process. WhatsApp sends a temporary code via SMS or a phone call during registration which the users must enter to authenticate their control over the phone number and SIM card for their account. “Since all accounts must go through registration before being able to send any messages, it is an effective starting point to concentrate our efforts.”
At the registration stage, if the systems detect a similar phone number that has been recently abused or if the computer network used for registration has been associated with suspicious behavior, it bans them before the registration itself via the machine learning system, nipping the problem at the bud.
Our goal is to identify and stop abusive accounts as quickly as possible, which is why identifying these accounts manually is not realistic. Instead, we have advanced machine learning systems that take action to ban accounts, 24 hours a day, 7 days a week – WhatsApp Team
The second stage, the messaging stage involves evaluation of the accounts’ behaviour in real time, banning accounts based on the intensity of user activity. To cite an example, the chat app’s machine learning system will ban those accounts that within five minutes of the registration attempt to send 100 messages in 15 seconds or quickly create dozens of groups or add thousands of users to a series of existing groups, or in other words, attempt to spam and disrupt the smooth running of the app.
The machine learning system also targets automation by keeping an eye at the top of a chat thread when a user is typing.
Spammers attempting to automate messaging may lack the technical ability to forge this typing indicator. If an account continually sends messages without triggering the typing indicator, it can be a signal of abuse, and we will ban the account – By company’s statement
The 3rd stage when the company receives negative feedback, (when other users submit reports or block the account) against an account, the case is evaluated by the detection mechanism with the appropriate follow-up action.
When a user sends a report, our machine learning systems review and categorise the reports so we can better understand the motivation of the account, such as whether they are trying to sell a product or seed misinformation – WhatsApp says about the feedback
WhatsApp is keen to bounce back from the fake news debacle it encountered last year, by way of introducing variety of new features and informative programmes in countries like India ( so as to educate users about detection of fake news) and it seems good to go on in its goal of removing abusive accounts, spammers beware!