A crucial aspect common to many areas of our life is the huge amount of data generated daily. This data covering business, software development, sociology, and other important domains provides a rich source of useful information that can support decision making. This brings the need for efficient yet effective data analytics approaches.
A crucial challenge is the effective analysis of heterogeneous data sources. In many scenarios, the situation is similar to the story of “The blind men and an elephant”; often we have various pieces of information on a particular topic spread out in various data sources. Individually, the information might be of limited use and might even be contradictory to one another. However, by integrating them together we could get the complete picture which could guide a decision maker to make a wise decision. Data resides in different forms, ranging from unstructured data on the web to highly structured data in relational database systems. Many research studies often focus on only one kind of data source, either unstructured or structured. However, as the complexity of data increases, we could no longer only analyze one source of data independent from others as we would then miss much information just like the blind men in the story. Motivated by this, my research goal is to holistically integrate and analyze heterogeneous data sources.