The Difference between Variable-based and Context-based Networks of Data Using Data Jackets

In recent years, the expectations for cross-disciplinary data exchange and collaboration have been rising. However, creating a data-driven innovation by coordinating data across different fields first requires a correct understanding of structures and relationships of existing data. It thus is important to investigate the structural characteristics of the population of data rather than analyzing individual data. Data Jacket (DJ) is a framework for describing an overview of data while keeping data itself confidential. This paper utilizes DJs to quantitatively assess overall trends and characteristics of data and to understand the structure and system of data with their variables and contexts. Results of the analysis revealed the networks of data via variables and contexts are different comparing their structural characteristics. The result suggested that even if data cannot be connected only with variables, the common usage contexts can combine the related data for solving problems.