A Knowledge Graph Approach towards Re-structuring of Scientific Articles

With expedition of huge number of research articles published in each domain, retrieval of relevant articles based on researcher's interest and requirement have become challenging. Further, there are circumstances where a researcher may not get the specific information sought after, regardless of whether it is there in the document collection. This is since the article in database is structured only based on title and citation data while the conceptual information and algorithms described inside an article are disregarded. In this work, we propose a useful methodology for re-structuring documents in the database by considering the document as a whole and representing the keywords and key-phrases extracted from the article data using Knowledge Graphs. Clustering of nodes of graph segregate articles into different domains and sub-domains. Knowledge graph is further explored to identify most important documents using modularity and then the documents are sorted based on relevance. Thus, proper structuring of the documents helps the researchers to recognize applicable content from a large database in short span of time since database associated with the query system is improvised. This technique is beneficial to all the researchers who are trying to resolve a problem by identifying apt documents for information need.