A Gradient Boosted Decision Tree-Based Influencer Prediction in Social Network Analysis

Twitter, Instagram and Facebook are expanding rapidly, reporting on daily news, social activities regional or international actual occurrences. Twitter other platforms have gained popularity because they allow users to submit information, links, photos videos with few restrictions content. As a result of technology advances (“big” data) an increasing trend toward institutionalizing ethics regulation, network analysis (SNA) research is currently confronted serious ethical challenges. A significant percentage human interactions occur networks online. In this instance, content freshness essential, as declines time. Therefore, we investigate how influencer (i.e., posts) generates interactions, measured by the number likes reactions. The Gradient Boosted Decision Tree (GBDT) Chaotic Gradient-Based Optimizer required for estimation (CGBO). Using earlier group develop Influencers Prediction issue in study’s setting SN-created groups. We also provide GBDT-CGBO framework efficient method identifying ability influence future behaviour others. Our contribution based logic, experimentation analytic techniques. goal paper find domain-based influencers using that uses semantic machine learning modules measure predict users’ credibility different domains at times. To solve these problems, will focus co-authorship economic instead online networks. results show our both useful effective. Based test results, model can correctly classify unclear data, which speeds up processing makes it more efficient.