Relational Learning Analysis of Social Politics using Knowledge Graph Embedding

Abstract

Knowledge Graphs (KGs) have gained considerable attention recently from both academia and industry. In fact, incorporating graph technology and the copious of various graph datasets have led the research community to build sophisticated graph analytics tools. Therefore, the application of KGs has extended to tackle a plethora of real-life problems in dissimilar domains. Despite the abundance of the currently proliferated generic KGs, there is a vital need to construct domain-specific KGs. Further, quality and credibility should be assimilated in the process of constructing and augmenting KGs, particularly those propagated from mixed-quality resources such as social media data. This paper presents a novel credibility domain-based KG Embedding framework. This framework involves capturing a fusion of data obtained from heterogeneous resources into a formal KG representation depicted by a domain ontology. The proposed approach makes use of various knowledge-based repositories to enrich the semantics of the textual contents, thereby facilitating the interoperability of information. The proposed framework also embodies a credibility module to ensure data quality and trustworthiness. The constructed KG is then embedded in a low-dimension semantically-continuous space using several embedding techniques. The utility of the constructed KG and its embeddings is demonstrated and substantiated on link prediction, clustering, and visualisation tasks.

An Intelligent Hybrid Model for Identity Document Classification

“…Others described it as repetitive regions of pixels in an image. Regardless of the definitions, the texture feature approaches are classified into seven categories: statistical, structural, transform-based, model-based, graph-based, learning-based, and entropybased 1,41,75 .…”

“…The shape feature extraction methods are contour-based and region-based. (1) The contour methods focus on the boundary. ( 2) the region methods consider the entire region 62,77 .…”

“…No prior knowledge or human intervention is required for this process 59 . Nath et al 67 proposed four steps in this technique: (1) Clustering the data, (2) All pixels are then classified based on clusters, (3) spectral class-map, (4) cluster labeling done by the analyst, (5) map the informational class. K-means clustering algorithm is an example of an unsupervised classification approach 39,69,72 .…”

“…Tables 4 and 5 represent the confusion matrix, in addition to the information such as sensitivity, specificity, and accuracy of the SIFT and OCR-based classification, as well as the proposed fusion model, obtained from ROC analysis which is used to analyze the performance of the algorithm. The analysis is a binary analysis in which the classification result is either true (1) or false (0), therefore TP and TN values are equal, similarly, FP and FN values are equal.…”

“…For example, the UK government in 2012 started a trusted online communications and public services channel which provides various digital services and supported 14 million visitors per week in 2019. In Australia, myGov 1 is the secure way to access the government's digital services, such as job search, taxation office, and child support. The three strategic priorities for the digital transformation of the Australian government are: easy to deal with, driven by users, and fit for every user.…”