Fahd, K, Miao, Yuan ORCID: 0000-0002-6712-3465, Miah, Md Shah Jahan M ORCID: 0000-0002-3783-8769, Venkatraman, S and Ahmed, Khandakar ORCID: 0000-0003-1043-2029 (2022) Knowledge graph model development for knowledge discovery in dementia research using cognitive scripting and next-generation graph-based database: a design science research approach. Social Network Analysis and Mining, 12 (61). ISSN 1869-5450

Abstract

Recent studies report doubling numbers of deaths due to dementia. With such an escalating mortality rate related to cognitive decline diseases, like dementia, timely information on contributing factors and knowledge discovery from evidence-based repositories is warranted. A large amount of scholarly knowledge extracted from research findings on dementia can be understood only using human intelligence for arriving at quality inferences. Due to the unstructured data presented in such a massive dataset of scientific articles available online, gaining insights from the knowledge hidden in the literature is complex and time-consuming. Hence, there is a need for developing a knowledge management model to create, query and maintain a knowledge repository of key elements and their relationships extracted from scholarly articles in a structured manner. In this paper, an innovative knowledge discovery computing model to process key findings from unstructured data from scholarly articles by using the design science research (DSR) methodology is proposed. The solution caters to a novel composition of the cognitive script of crucial knowledge related to dementia and its subsequent transformation from unstructured into a structured format using graph-based next-generation infrastructures. The computing model contains three phases to assist the research community to have a better understanding of the related knowledge in the existing unstructured research articles: (i) article collection and construction of cognitive script, (ii) generation of Cypher statements (a knowledge graph query language) and (iii) creation of graph-based repository and visualization. The performance of the computing model is demonstrated by visualizing the outcome of various search criteria in the form of nodes and their relationships. Our results also demonstrate the effectiveness of visual query and navigation highlighting its usability.

Search Google Scholar

Repository staff login