On February 26, IT Home reported that the official of Ditto released an announcement this week announcing multiple measures to prevent online violence. It was the first to launch functions such as "comment and post warning".
The announcement shows that Ditto has comprehensively upgraded the platform's ability to prevent online violence, providing users with eight functions to comprehensively manage comments and private messages. Among them, for improper private messages, newly launched "risk warning" and "negative content filtering" and other functions; For the improper comments that have been sent, the first "sending alert" function in China will be launched soon for interception.
Data shows that Diaoyin generates 800 million comments every day, of which 32.79% are "abusive and personal attacks" among improper comments complained, reported and finally handled.
IT home learned that for comments, Tiao Yin is going to launch the first "sending alert" function in China. In this function, if the system model determines that there is a problem with the comments that have been sent, it will push a pop-up reminder to suggest the sender to edit again to remove improper comments. If the sender insists on sending, the comment will not appear in the comment area. Recently, small scale test has been started for this function.
Previously, Ditto has launched three functions, namely, "hierarchical management of comment permissions", "keyword screening" and "comment selection". Under "Hierarchical management of comment permissions", users can set comment permissions through "Permission Settings - Advanced Settings - Who can comment". According to their own needs, users can choose who can comment on their own published content from the four options of "Everyone", "Only Fans", "Only Interrelated Friends" and "Only Yourself".
In terms of private messages, dithering adds two new functions: "user risk alert" and "negative content filtering". Under the "User Risk Reminder" function, when the system model identifies that there is a risk in the stranger's private message that the user just received, a pop-up window will be pushed to the user to prompt him/her "whether he/she knows the user". If the user selects "Don't know", the system will pop up a window again, prompting the user to "blackmail, report, remove fans" and other operations. At present, this function will send risk alerts to 250000 sessions every day.
Under the "Negative Content Filtering" function, when the model determines that the private message received by the user is "abusive or harassing", the message will be directly put into the "Stranger Box - Junk Information". In addition, Tiao Yin also launched the "Warm Baby" assistant, which can alleviate the negative emotions of users through the interactive way of message dialogue according to the emotional tendency of users' content.