Semantic proximity with linked open data: A concept for social media analytics

The raw unstructured big data created on social networking platform is having great potential to generate various trends. In this work, we propose a novel approach for meaningful social network data mining with integration of semantic web and linked open data concepts. We propose a semantic proximity based data mining process in our framework for the analysis of employment trends using LinkedIn. The data extraction algorithm and semantic based results are presented which describes the real time dataset and its integration with linked data. We compare different linked data formats to evaluate our results and identify our format of data expression. The process of social data analytics by integrating background knowledge from global linked data is the core concept of our research work.