Analysis of University Social Media User Engagement by Topic

Social media is currently one of the primary platforms for spreading information about organizations or companies, including universities. To reach more users, we need to analyze user engagement. Topic essential feature attract interest on a post. Therefore, by understanding topic preference, can increase In this study, identify posts using Latent Dirichlet Algorithm (LDA) method. Furthermore, predict engagement scores (number likes and comments) decision tree random forest The experimental results show that there are 11 topics identified LDA, after analyzing further at three different levels (views, likes, comments), most engaging achievement. prediction reveal performs better than tree, with MAE score 1074