Newtral has presented the prototype of FactFlow, an artificial intelligence tool Designed to track disinformation circulating on Telegram with real-time updates. The launch is part of a Journalism AI event, where the work developed by the winning projects of the Innovation Challenge will be showcased.
The objective is clear: speed up the detection of misleading content and offer fact-checking teams a dashboard that highlights trends and false narratives within the platform. Telegram is one of the places where hoaxes circulate the most in Spain, and FactFlow aims to reduce time that verifiers now dedicate to manually following channels and messages.
What is FactFlow and what does it offer?
FactFlow combines automatic analysis of text, audio, video and images to identify disinformation patterns and group them by topic. The system features a real-time alert panel that helps prioritize cases, detect peaks in activity, and track the progress of coordinated campaigns within Telegram channels and groups.
The tool was born after a nine-month Innovation Challenge, in which 35 media outlets from different countries participated. In addition to its technical focus, It stands out for its practical application: offers an operational view of trends and actors, useful for newsrooms that need speed and context when a hoax starts to go viral.
How the system works and how to train it
The start is from a human selection of accounts that spread disinformation. With that initial set, the AI ​​learns to locate similar messages and channels, expand the source map, and recognize recurring patterns, from repeated narratives to multimedia formats that are systematically rejected.
This hybrid approach allows extend tracking continuously: The machine proposes new nodes and verifiers validate and adjust the model. The result is a feedback loop that reduces manual monitoring and gain coverage without losing editorial control over what is labeled as disinformation.
Preliminary results and scope
To date, the system has processed more than 10 million records and has flagged more than 125.000 messages with indications of disinformation. Approximately 70% are in Spanish, although there are also significant volumes in Russian, English, German and Portuguese, which highlights the transnational nature of many campaigns.
During episodes of high news impact, such as the DANA in the Valencian Community, multiple Telegram accounts replicated rumors and falsehoods at high speed. Tools like FactFlow allow you to see this acceleration on the dashboard and act before it false narratives take root in public conversation.
Why Telegram encourages the spread of hoaxes and fraud
Telegram offers features that facilitate the operation of disinformation networks: agile account creation, possibility of using disposable numbers and mass management of groups and channels. This ecosystem, coupled with the perception of greater privacy, makes it an attractive environment for actors seeking anonymity and persistence.
In addition, the platform allows the use of bots and automations via API, with programmed responses and actions that reduce human effort to scale campaigns. In practice, some contact with victims or message dissemination may be handled by automated systems, which multiplies the reach at little cost.
Another key point is the ease of bring up conversations from services with payment protections or strict moderation and take them to channels and chats where those safeguards don't apply. When this happens, the user loses barriers that could stop scams or recover funds, leaving you exposed to more direct pressure and deception.
The combination of temporary accounts, automation and large audiences in channels makes Telegram a effective platform for coordinating misinformation and fraud, and that is why many consider it among the alternatives to Twitter. Precisely for this reason, technological initiatives such as FactFlow focus on mapping trends and accelerate the journalistic response.
Implications for newsrooms and citizens
For verification teams, FactFlow means fewer hours of manual tracking and more time to investigate, contextualize, and refute with evidence. Having comparable alerts and analytics across channels makes it easier to detect points of origin and repeated tactics, from video recycling to audio manipulation.
For users, it is a call to maintain verification habits On Telegram: check sources, be wary of screenshots and audio recordings of dubious origin, and report spam or suspicious channels and don't share unverified content. Fighting disinformation is also a matter of daily digital hygiene.
The FactFlow presentation shows how journalism can be supported by Applied and auditable AI to keep track of disinformation on Telegram, with data, context, and helpful alerts when the conversation picks up speed and hoaxes try to override verified facts.