Springer’s Social Network Analysis and Mining (SNAM), a prestigious journal, publishes groundbreaking research at the intersection of computational and information sciences discipline and the social science discipline. Recently, SNAM published one of our studies titled, “KG-CFSA: A Comprehensive Approach for Analyzing Multi-source Heterogeneous Social Network Knowledge Graph,” the authors develop methods to fuse multisource heterogeneous data through knowledge graphs and contextual focal structure analysis for improving the state of the AI models that feed on such open datasets. Their paper names this method as KG-CFSA.
Specifically, the authors integrate data from multiple social networks, knowledge graph fusion, and contextual focal structure analysis to model relations across documents, entities, and topics. The method applies Cartesian merge techniques and enhances information with third-party data from WikiData and DiffBot. When applied to an Indo-Pacific region dataset, the system identified 40,000 unique focal sets discussing economics, elections, and policies. The approach effectively tracks information spread across multiple social media platforms and enhances visibility of vital information through various relationships, demonstrating KG-CFSA’s effectiveness in contextualizing large-scale multi-source information. For the Indo-Pacific dataset, KG-CFSA successfully extracted meaningful focal structures related to economic, political, and governmental discussions involving Indonesia and China.
Prof. Agarwal said, “This approach effectively contextualizes large-scale information flow and identifies focal structures that shape online discourse about significant regional matters, such as the Indo-Pacific Economic Framework and Belt and Road Initiative conversations. Moreover, this study develops ways to help improve AI model training by fusing multisource and heterogeneous open data across different platforms contextualized through knowledge graphs.” Click here to read the full article.
The journal SNAM focuses on the theoretical and practical aspects of social network analysis and data mining. It covers interdisciplinary research in fields such as computer science, sociology, physics, economics, and more. Some key themes and ideas covered in SNAM are
- Social network structures and dynamics,
- Data mining and machine learning for networks,
- Computational and algorithmic approaches,
- Influence, diffusion, and community detection, and
- Applications in social media, marketing, and behavioral analysis