5 Questions with Ksenia Iluik, Co-founder of LetsData

Ukrainian Startup Uses Machine Learning to Combat Coordinated Misinformation Campaigns

LetsData, a Ukraine-based tech company, has developed sophisticated machine learning systems that identify coordinated bot campaigns and misinformation efforts on social media before they can cause widespread damage. The system scans millions of posts daily across multiple platforms, detecting unusual patterns and providing organizations with actionable intelligence to counter false narratives.

Co-founders Ksenia Iliuk and Andriy Kusy established LetsData after witnessing firsthand how traditional monitoring tools fell short in tracking information operations. “Existing tools like keyword-based social media trackers and brand-monitoring systems reacted too slowly and flagged problems only after a misinformation campaign had already spread,” explained Iliuk in a recent interview with the Center for Data Innovation.

The company’s founding was driven by the need for more proactive solutions in an environment where disinformation campaigns have become increasingly sophisticated and frequent. In 2021 and 2022, Iliuk and Kusy began experimenting with machine learning models designed to detect early warning signs of coordinated activities, such as synchronized posting behavior and suspicious account creation patterns.

LetsData’s approach differs from conventional monitoring systems by employing multiple machine learning models trained on real examples of previous bot campaigns. These models analyze millions of posts daily across various platforms and languages to identify anomalous activities that typically indicate coordinated manipulation.

“If 50 new Facebook accounts appear simultaneously from the same IP address or share similar profile traits, that’s an anomaly that isn’t typical user behavior,” Iliuk noted. The system flags suspicious patterns such as identical hashtags spreading rapidly across unrelated accounts or newly created profiles repeatedly sharing the same links.

When potential threats are identified, the platform automatically generates alerts and detailed reports for clients, which include governments, financial institutions, and consumer brands. Each report contains multi-step recommendations for countering the identified misinformation, from flagging false content to issuing public clarifications and engaging with affected audiences.

The company maintains what it calls a “human-in-the-loop approach,” where experts guide model training, validate outputs, and confirm that alerts are both relevant and actionable. This combination of automation and human oversight allows LetsData to detect emerging campaigns early while maintaining reliability.

According to Iliuk, one of the biggest challenges facing the anti-misinformation industry is the increasing sophistication of bad actors who now leverage AI tools themselves. “In the past, bot networks were easier to detect because their messages were repetitive, poorly formatted, or filled with grammatical errors,” she explained. “Today, AI tools enable bots to maintain consistent identities, engage in realistic conversations, and execute scams with minimal human oversight.”

This evolution has allowed malicious actors to combine scale and quality, deploying large numbers of convincing bots that are harder to identify as fraudulent. LetsData counters this by continuously adapting its models to recognize new patterns and techniques.

The company’s approach also offers economic advantages over traditional detection methods. While spreading misinformation is relatively inexpensive for bad actors, defenders historically faced high costs because they needed separate specialized detection systems for each platform or scenario. LetsData’s core machine learning models can be rapidly adapted to different contexts, enabling more cost-effective monitoring across multiple platforms.

In one notable case study, LetsData helped a U.S. company counter a sophisticated impersonation campaign ahead of an AI product launch. The bot campaign, originating from Vietnam, created AI-generated advertisements mimicking the company and claiming its product had already launched, directing users to fake chatbots designed to distribute malware. LetsData detected this threat early, allowing the company to take swift action and protect both its users and reputation before the official product launch.

As misinformation tactics continue to evolve, companies like LetsData represent a growing sector of technology focused on maintaining information integrity across digital platforms, particularly as AI tools become more accessible to both defenders and malicious actors alike.