OK launched a new content recommendation system focused on author posts
The Odnoklassniki (OK) social network has launched a new version of the content recommendation system, which focuses on the author’s posts, according to a press release received by the editors of Lenta.ru.
The innovations will allow bloggers and groups to get more views and attract new audiences. “Now the algorithms are learning to give audience to as many authors as possible and thus increase the variety of content on the platform: both in the “Recommendations” section and in the recommended content block in the feed,” the message says.
For each post, the neural networks will select the most relevant audience based on user activity and interests. It will also help writers who publish on more specialized topics like science or extreme sports.
In addition, the COs reviewed the approach to content quality in the recommendations. Now the social network does not recommend groups and profiles to users that have low image or video quality, clickbait, as well as a large amount of non-original content. The new system is already running on all platforms.
Previously, Odnoklassniki launched the annual campaign “Invaluable Lesson”. From September 1 to October 5, users will be able to thank teachers: Teachers will be able to see congratulations from current and former students on Teacher’s Day.
*The article has been translated based on the content of lenta.ru. If there is any problem regarding the content, copyright, please leave a report below the article. We will try to process as quickly as possible to protect the rights of the author. Thank you very much!
*We just want readers to access information more quickly and easily with other multilingual content, instead of information only available in a certain language.
*We always respect the copyright of the content of the author and always include the original link of the source article.If the author disagrees, just leave the report below the article, the article will be edited or deleted at the request of the author. Thanks very much! Best regards!