An application to get rid of inappropriate phrases in the posts of the social media platforms that you use
In social networks, some are subjected to inappropriate comments and insults in the responses or comments from unethical followers, and although this type of speech prompts hate speech, we find that these behaviors are increasingly prevalent in social platforms, and for this reason the company The French emerging Bodyguard has developed a distinct application to discover comments and harmful content and block them so that they do not reach the users, the application was directed to the citizens of France as it was focusing on French content several years ago, and now it has also been launched for the English-speaking market, and the estimated number of Bodyguard users is more than 50,000 users In France, thanks to the application's artificial intelligence technology, it is able to detect negative and abusive comments with an accuracy of between 90 and 95% and thus protect against cyberbullying, and the application supports well-known social networks such as Twitter, YouTube, Instagram and Twitch, and unfortunately not He canProcessing content in Snapchat and TikTok due to API limitations there.
The way to work in the application is very simple, first you go to this link , then select the type of your operating system.
Then you log into your social media accounts and choose the rate of "supervision", as the application has several categories such as: insults, physical scandal, bullying, sexual harassment, racism, and in each of these categories the user can set the level of moderation between high And medium and low.
Once the appropriate moderation rate is configured, the user no longer needs to log into the app again unless he needs to update any of the previous moderation levels, as the app works in the background and checks comments and social media posts to determine whether the content is negative or not, and Bodyguard scans the responses and comments from its servers and makes the right decision about them, for example it can hide comments, mute and block users, etc., and the next time you open the application you will find that the content is safe.
The application cleans the offensive comments in a mathematical way and tries to analyze the content of the comment in its context, and it can determine whether the comment is offensive to you, an external person, or a group of people ... etc.