This study explores the complex situation in the Sahel region, an area characterized by continuous social conflicts and significant political instability. It presents an early warning system developed to predict violence across 12 Sahelian countries, focusing on the urgent need for accurate forecasting to guide policy decisions and predict catastrophic events. Utilizing historical data, the system predicts fatalities at both national and regional level, in order to enable policymakers and stakeholders to take appropriate action in a timely manner, given the expected conflict. Central to the study is the integration of data from multiple sources. In particular, GDELT provides structured information extracted from online news articles relevant to regional conflict dynamics, while ACLED offers a comprehensive dataset on political violence, protests, and associated events worldwide.