INTELLIGENT DETECTION OF MALICIOUS SOCIAL MEDIA PROFILES USING MULTI-DIMENSIONAL ANALYTICS

Abstract

The rapid growth of social media platforms has significantly increased online communication and information sharing. However, it has also led to the emergence of malicious profiles, fake accounts, bots, and fraudulent users that spread misinformation, perform phishing attacks, and manipulate online communities. Detecting such malicious profiles has become a critical challenge for maintaining trust and security in social media ecosystems. This research proposes an Intelligent Detection System for Malicious Social Media Profiles using Multi-Dimensional Analytics. The proposed framework analyzes multiple dimensions of user behavior, including profile attributes, content activity, network relationships, and temporal interaction patterns. By integrating these diverse data sources, the system can effectively identify suspicious behaviors that indicate malicious intent. Machine learning and data analytics techniques are employed to process large volumes of social media data and classify users as legitimate or malicious. The framework extracts key features such as posting frequency, follower–following relationships, content similarity, and engagement patterns. These features are then analyzed using advanced classification algorithms to detect abnormal patterns associated with fake or harmful accounts. The proposed system improves detection accuracy by combining behavioral analysis, content analysis, and network analysis in a unified multi-dimensional framework. Experimental results demonstrate that the approach can effectively identify malicious profiles while reducing false positives. This research contributes to enhancing trust, security, and reliability in social media platforms, helping to protect users from harmful online activities.