Prototypical implementation of methods to extract frequent patterns from tweets representing migration drivers

It will focus on the scalability aspect of the current pattern mining approaches when analysing huge number of tweets We will take into account algorithms for distributedcomputing using existing platforms such as Hadoop Apache Spark As such deep analysis may differ based on the language used this deliverable will pay special attention to understudied languages It will prototypically implement the methods to extract frequent patterns from tweets representing migration intentions