In an effort to better understand how trolls and spammers work on social media, Facebook is developing bots that can imitate such people and help the company better identify trolls and scammers on its platform. To achieve this, Facebook has built a scaled-down version of its main platform to simulate user behavior.
The company’s researchers have released a paper on a “Web Enabled Simulation” (WES) for testing the platform where nonexistent users can like, share, and a friend or harass abuse, and scam away from human eyes. In this way, Facebook engineers will be able to identify and fix the undesired consequences of new updates before they’re deployed.
According to the report from MIT Technology Review, the platform on which the company is doing this research is called “WW” that automatically recommends changes that can be made to the platform to improve the community experience.
“But the sorts of debugging methods that normal-size companies use aren’t really enough when you’ve got 2.5 billion users. Such methods usually focus on checking how a single user might experience the platform and whether the software responds to those individual users’ actions as expected,” said the MIT report.
As per the report, around 25 percent of Facebook’s major issues have emerged only when the users begin interacting with one another. Facebook simulates hundreds to thousands of its users at a time with the help of hard-coded and machine-learning-based bots.
“While the scenarios play out, the system automatically adjusts different parameters in the simulation, such as the bots’ privacy settings or the constraints on their actions,” the report mentioned.
Well, this WW is built directly on the live platform instead of a separate testing platform. However, the bots work behind the scene to make it look like a real environment.
“While a typical user interacts with Facebook through a front-end user interface, such as a profile and other website features, fake bot users can interact directly with the back-end code,” the report said.
In this way, this platform will work with real people that will make the research team easier to understand the flaw and security issues on the platform. This could help Facebook detect bugs faster in the future.
For the latest tech news and updates, Install TechCodex App and follow us on Google News, Facebook, and Twitter. Also, if you like our efforts, consider sharing this story with your friends, this will encourage us to bring more exciting updates for you.