In the digital marketing landscape, pinpointing key influencers within social networks is essential for optimizing brand outreach and engaging audiences effectively. This research delves into the use of Social Network Analysis (SNA) combined with sophisticated machine learning techniques to enhance the precision of influencer identification. By utilizing a detailed dataset with various network metrics, we apply Logistic Regression, Random Forest, Stacking Classifier, and Gradient Boosting Classifier to develop predictive models for identifying influencers. In addition, Kmeans clustering is employed to categorize users based on their network characteristics, thereby refining the accuracy of our predictions. The target variable, known as 'Choice,' is derived from analyzing network features such as follower numbers, mentions, retweets, and posts. The integration of SNA with these machine learning models not only boosts the reliability of identifying influencers but also offers deeper insights into the structural patterns within social networks. This comprehensive approach showcases the effectiveness of datadriven techniques in enhancing influencer marketing strategies.

Keywords: Influencer Identification, Social Network Analysis, Machine Learning, Predictive Models, Kmeans Clustering, Digital Marketing Strategies