The increasing spread of social media has equally increased the spread of disinformation and misinformation, which poses a significant risk to democracy, journalism, and public trust. In particular, spreading fake news leads individuals to make decisions based on fake information. To solve this problem, artificial intelligence can assist humans in detecting fake content. This paper presents a system design that seeks to evaluate the spreading of news as either real or fake using techniques like Machine Learning (ML), Deep Learning (DL), and Natural Language Processing (NLP). Developed micro-services architecture leverages learning-based mechanisms to analyze user’s reactions and profiling mechanisms for community detection. Using stylometric and sentiment analysis techniques, the system analyzes behavioral patterns of disinformation and associating them with relevant target audiences. The proposed approach integrates STIX-represented attacks with the tactics, techniques, and procedures defined by the DISARM framework, providing a structured view of attacks and countermeasures to improve response strategies.