Network Science based Predictive Analysis on Social Media Data

Abstract

Traditional approaches utilizing machine learning algorithms have limitations in capturing the full depth and semantic nuances of text, hindering comprehensive analysis for tasks like opinion mining, sentiment analysis, population health analytics etc. To overcome these limitations, we propose the integration of graph analysis and Social Network Analysis (SNA) techniques to enhance the informative value of tweet analysis and facilitate the extraction of structured knowledge from textual and visual content. This work focuses on modeling user-generated content on Twitter to enable intelligent population analytics applications in the healthcare domain. Standard datasets comprising user details and their tweets are considered for the experiments, which are transformed into graph representations suitable for both structural and behavioral analytics. Additionally, a comparative study to assess the impact of varying network sizes by manipulating the number of nodes within the network is conducted. To evaluate the network properties, different centrality measures were employed and compared. © 2023 IEEE.