Quantifying and Bursting the Online Filter Bubble

Abstract

In this thesis, we develop methods to (i) detect and quantify the existence of filter bubbles in social media, (ii) monitor their evolution over time, and finally, (iii) devise methods to overcome the effects caused by filter bubbles. We are the first to propose an end-to-end system that solves the problem of filter bubbles completely algorithmically. We build on top of existing studies and ideas from social science with principles from graph theory to design algorithms which are language independent, domain agnostic and scalable to large number of users.