Increasing Marketing Campaign Performance Using Influential Users in Social Networks
In recent years, with the emergence of online social networks and the growing interest in genetics and biological networks, the research community has been tasked with analyzing knowledge extracted from multirelational datasets. Such analysis, generally known as Knowledge Discovery in Databases (KDD), is concerned with the computer aided discovery of useful knowledge in databases. An example of the extracted knowledge would be user interest data which improves the accuracy on viewing and predicting market trends, and allows for enriched customization and customer targeting. In this research we are interested in techniques for analyzing multi-relational datasets. Formal Concept Analysis (FCA), a powerful pattern extraction technique, has been used successfully for analyzing non-relational entities. But with the introduction of Relational Concept Analysis (RCA), an extension of FCA, it is possible to apply it on multi-relational datasets. Our goal is to transform the robust FCA based data mining techniques for non-relational datasets, into techniques applicable on multi-relational databases with the use of RCA. We plan to apply these techniques on heterogeneous social networks as a test-bed for multi-relational datasets.