Social network data analysis

Project description:

Project aims to collect and analyse data from all popular social networks such as twitter, instagram and youtube. We designed BigData engineering and data collection pipeline, which already aggregated 1+ Billion entries from social networks. These entries mostly belong to the influencers and celebrities. In the scope of the project we also have implemented the fake account detection algorithm, generating the statistics about the number of followers of the users and comments on particular posts. Database entries are growing on an hourly basis and every new account is validated, hence possible to identify how many fake and real accounts certain celebrity or influencer have.

Technologies:

• Python, RabbitMQ, Elastic Search, Neo4j, Kubernetes.