In an era of social media manipulation and misinformation, we could surely use the help of innovative entrepreneurs. Social media is now critical to the way the public consumes and shares news. But these networks were never built for informed debate on the news. They were built to reward virality. That means they are open to manipulation for commercial and political purposes.
Fake social media accounts (bots (automated) and “sock puppets” (human-run)) can be used in a highly organized way to spread and amplify minor controversies or fabricated and misleading content, which will eventually influence other influencers. and even in news organizations. And brands are very open to this threat. Using such disinformation to discredit brands has the potential for a very costly and damaging disruption when up to 60% of a company’s market value may be in its brand.
Astroscreen is a startup that uses machine learning and misinformation analysts to detect manipulation of social media. Now it has secured $ 1M in seed funding to advance its technology. And he has an inheritance that suggests that he at least has a chance of achieving this.
Its techniques include coordinated activity detection, linguistic fingerprinting, and fake account and botnet detection.
The funding round was led by Speedinvest, Luminous Ventures, UCL Technology Fund, which is managed by AlbionVC in collaboration with UCLB, AISeed and the London Co-investment Fund.
Astroscreen CEO Ali Tehrani previously founded a machine learning news analytics company that he sold in 2015 before fake news got widespread attention. He said: “While building my old new company, I saw firsthand how polarized and biased news articles were being artificially shared and amplified by a large number of fake accounts. This gave the stories high levels of exposure and authenticity that they would not have had on their own. “
Juan Echeverría, CTO of Astroscreen, whose Ph.D. At UCL, the detection of fake accounts on social media made headlines in January 2017 with the discovery of a massive botnet managing some 350,000 separate accounts on Twitter.
Ali Tehrani also believes that social media is effectively hiding below the waterline in this whole problem: “Social media platforms themselves cannot solve this problem because they are looking for scalable solutions to maintain their software margins. If they dedicated With enough resources, their earnings would be more like a newspaper editor than a tech company, so they focus on spotting collective anomalies – accounts and behavior that deviate from the norm for their user base as a whole. But this is only good for detecting spam accounts and highly automated behavior, not the sophisticated techniques of disinformation campaigns. “
Astroscreen takes a different approach, combining machine learning and human intelligence to detect contextual (rather than collective) anomalies – behavior that deviates from the norm for a specific topic. It monitors social media for signs of disinformation attacks, informing brands if they are being attacked in the early stages and giving them enough time to mitigate any negative effects.
Lomax Ward, Partner at Luminous Ventures, said: “Social media abuse is a major social problem and Astroscreen’s defense mechanisms are a key part of the solution.”