This Project is based on Data analytics. In this project we have discovered various models which are used to predict social media polarisation. I have implemented these models with suitable changes on different type of datasets. In this research we have considered different models and their implementation to derive differences among all the opinions of the individual based on the algorithms.We have first studied the dynamics of opinion formation under random interactions with a fixed rate of communication between pairs of agents.We have studied voter model and its extensions to study the opinion based on neighbours with also considering opinion exchange processes inspired by the Sznajd model. We have described the structure of the social network statistically, assuming that the number of contacts of a given individual determines the probability that their opinion reaches and influences the opinion of another individual. At the end, we have compared different graphs on the basis of the change in concentration of voters with positive opinion in each iteration. It further provided us with the judgement of identifying the most efficient algorithm among all. Types of dataset- dataset folder- in this folder, I have implemented various models on real world dataset i.e facebook dataset. random folder-I have implemented these models by generating the graph of the network using random functions of python. specific folder- I have implemented the models on that network graph where I have applied specific conditions on connection between the edges. facebook dataset-It's the dataset we have of a facebook networkn consisting of connection of edges. excel sheet- it is consists of graph comparing different models of prediction of polarisation. Report-it cosnsists of deep analysis of our project and how we tested them on different type of datasets and at the end we have generated a graph to compare different models.
we are yet to test these models on more real world dataset and make more provisions in algorithms to make it more feasable for the real world.