TikTok launches a new model to better detect ‘borderline’ content
As part of its efforts to create a safe platform for all users, especially younger ones, TikTok is launching a new version of its borderline suggestive model. This model will automatically identify sexually explicit, suggestive, or borderline content. Therefore, helping TikTok to identify videos that do not necessarily violate its community guidelines but may not be suitable for younger audiences.
The new model aimed at creating a safer environment for younger users
According to TikTok, the updated model is more accurate and efficient at identifying content that may not be appropriate for all viewers. This is especially important given the popularity of the platform amongst teenagers. By more effectively identifying and removing this type of content, TikTok aims to create a safer and more family-friendly environment for its younger audience.
“We’re making progress to reduce the prevalence of borderline or suggestive content recommendations overall and are now launching the next iteration of our borderline suggestive model which we expect to improve detection of such content, therefore creating a more appropriate and comfortable experience for teen account holders,” TikTok said in a blog post.
Challenges in detecting and removing borderline content
While other platforms like Instagram have also tried to filter out borderline content from recommendations, it has historically been difficult for automated systems to consistently detect content with more “mature” themes that do not contain explicit nudity. This is because the line between “borderline suggestive” and acceptable content can be subjective. The company will need to ensure that the new model is fair and doesn’t unfairly remove content that some users may find acceptable.
TikTok did not provide specific details on how much more accurate the new system is, but the company said that it has “prevented teen accounts from viewing over 1 million overtly sexually suggestive videos” in the last 30 days.
As part of its efforts to create a safe platform for all users, especially younger ones, TikTok is launching a new version of its borderline suggestive model. This model will automatically identify sexually explicit, suggestive, or borderline content. Therefore, helping TikTok to identify videos that do not necessarily violate its community guidelines but may not be suitable for younger audiences.
The new model aimed at creating a safer environment for younger users
According to TikTok, the updated model is more accurate and efficient at identifying content that may not be appropriate for all viewers. This is especially important given the popularity of the platform amongst teenagers. By more effectively identifying and removing this type of content, TikTok aims to create a safer and more family-friendly environment for its younger audience.
“We’re making progress to reduce the prevalence of borderline or suggestive content recommendations overall and are now launching the next iteration of our borderline suggestive model which we expect to improve detection of such content, therefore creating a more appropriate and comfortable experience for teen account holders,” TikTok said in a blog post.
Challenges in detecting and removing borderline content
While other platforms like Instagram have also tried to filter out borderline content from recommendations, it has historically been difficult for automated systems to consistently detect content with more “mature” themes that do not contain explicit nudity. This is because the line between “borderline suggestive” and acceptable content can be subjective. The company will need to ensure that the new model is fair and doesn’t unfairly remove content that some users may find acceptable.
TikTok did not provide specific details on how much more accurate the new system is, but the company said that it has “prevented teen accounts from viewing over 1 million overtly sexually suggestive videos” in the last 30 days.
Denial of responsibility! Techno Blender is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – [email protected]. The content will be deleted within 24 hours.