Detecting Influencer Authenticity on Social Media Platforms using Machine Learning and Natural Language Processing Techniques

The growth of social media platforms has greatly increased the use of influencer marketing as an important strategy for brand promotion. However, the increasing presence of fake followers, automated bots, and manipulated engagement has made it difficult to accurately assess the authenticity of influencers. This creates serious challenges for brands when selecting trustworthy influencers for collaborations. To address this issue, this study proposes an Influencer Authenticity Analyzer that uses Machine Learning and Natural Language Processing (NLP) techniques to evaluate influencer credibility. The system analyzes numerical data such as follower count, likes, and comments, along with textual data including captions and user interactions. NLP techniques such as sentiment analysis and keyword extraction are used to understand content quality, while engagement metrics help identify unusual or suspicious patterns. In addition, the system includes features such as fake follower detection, fake comment identification, and influencer comparison, providing a more complete evaluation. The results are presented through an interactive dashboard with graphical visualizations, making it easier for users to interpret the findings. The system generates an authenticity score along with a classification result, helping users distinguish between genuine and fake influencers. Overall, the proposed approach offers a practical and effective solution for improving transparency in influencer marketing and supporting data-driven decision-making.