Odnoklassniki has launched a model based on machine learning that limits intrusive dating and communication with unwanted interlocutors on the social network, a representative of the company informed RB.RU.
OK users who often reject communication and dating will not receive notifications from intrusive interlocutors, for example, about friend requests, photo classes or posts, gifts, page views.
Cyberbullies will have a limited number of dialogues with users they do not know.
To protect users, OK analyzes real-time social interactions between unknown users and divides them into categories:
- The neural network finds accounts that regularly add people without mutual acquaintances as friends, send gifts to strangers en masse, give them classes, and write personal messages.
- The OK model includes people who often reject friend requests, blacklist users, reject gifts, or complain about the actions of strangers.
The model was tested on different OK audiences for several months; As part of the experiment, the number of complaints about intrusive attention from unknown accounts decreased by 25% compared to previous periods.
Previously, State Duma Deputy Chairman Vladislav Davankov (“New People”) proposed introducing a system for blocking cyberbullying and obsessive bullying on Russian social networks.
Author:
Anastasia Marina
Source: RB
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
