Context Aware Recommendation for Data Visualization
Visualization plays a major role in data mining process to convey the findings properly to the users. It is important to select the most appropriate visualization method for a given data set with the right context. Often the data scientists and analysts have to work with data that come from unknown domains; the lack of domain knowledge is a prime reason for incorporating either inappropriate or not optimal visualization techniques. Domain experts can easily recommend commonly used best visualization types for a given data set in that domain. However, availability of a domain expert in every data analysis project cannot be guaranteed. This paper proposes an automated system for suggesting the most suitable visualization method for a given dataset using state of the art recommendation process. Our system is capable of identifying and matching the context of the data to a range of chart types used in mainstream data analytics. This will enable the data scientists to make visualization decisions with limited domain knowledge.
READ FULL TEXT