Relational Learning Analysis of Social Politics using Knowledge Graph Embedding

Knowledge Graphs (KGs) have gained considerable attention recently from both\nacademia and industry. In fact, incorporating graph technology and the copious\nof various graph datasets have led the research community to build\nsophisticated graph analytics tools. Therefore, the application of KGs has\nextended to tackle a plethora of real-life problems in dissimilar domains.\nDespite the abundance of the currently proliferated generic KGs, there is a\nvital need to construct domain-specific KGs. Further, quality and credibility\nshould be assimilated in the process of constructing and augmenting KGs,\nparticularly those propagated from mixed-quality resources such as social media\ndata. This paper presents a novel credibility domain-based KG Embedding\nframework. This framework involves capturing a fusion of data obtained from\nheterogeneous resources into a formal KG representation depicted by a domain\nontology. The proposed approach makes use of various knowledge-based\nrepositories to enrich the semantics of the textual contents, thereby\nfacilitating the interoperability of information. The proposed framework also\nembodies a credibility module to ensure data quality and trustworthiness. The\nconstructed KG is then embedded in a low-dimension semantically-continuous\nspace using several embedding techniques. The utility of the constructed KG and\nits embeddings is demonstrated and substantiated on link prediction,\nclustering, and visualisation tasks.\n