A Comparative Analysis of Louvain and Leiden Coloring Algorithms in Influencer Detection

In today's digital era, the influence of social media influencers has grown significantly. A commonly used feature by business professionals today is follower grouping. However, this feature is limited to identifying influencers based solely on mutual followership, highlighting the need for a more sophisticated approach to influencer detection. This study proposes a novel method for influencer detection that integrates the Leiden coloring algorithm and Degree centrality. This approach leverages network analysis to identify patterns and relationships within large-scale datasets. First, the Leiden coloring algorithm is employed to partition the network into distinct communities, identifying potential influencer clusters. Subsequently, Degree centrality is utilized to identify nodes within these communities exhibiting high connectivity, indicating individuals with significant influence. The proposed method was validated using data crawled from Twitter (X) social media, employing the keyword "GarudaIndonesia." The data was collected using Tweet-Harvest between January 1, 2020, and October 16, 2024, resulting in a dataset of 22,623 rows. The proposed method was compared to the Louvain coloring method, demonstrating an increase in the modularity value of the Leiden coloring algorithm by 0.0195, a reduction in processing time by 13.93 seconds, and a decrease in the number of communities by 649.