A Framework for Quantifying Controversy in Attributed Networks: Biased Random Walk (BRW).

Hanif Emamgholizadeh, Milad Noorizadeh, Mir Saman Tajbakhsh, Mahdieh Hasheminezhad.


Societies, all over the world, have been much more bipolar in the past a few years, particularly, after the emergence of online social networks and media. Indeed, the gap between two ends of social spectrum is going to be even deeper after the outbreak of new media. In this circumstance, social polarization has been a growing concern among socialists and computer science expertise because of the detrimental impact which online social networks can have on societies by adding fuel to the fire of extremism.\
Several researches have been conducted for proposing measures to calculate controversy level in social networks, afterward, reducing controversy among contradicting viewpoints, for example, by exposing opinions of one side to other side’s members. Most of the attempts for quantifying social networks’ controversy have considered the networks in their most primary form, without any attributes. Although these kinds of researches provide platform-free algorithms to be used in different social networks, they are not able to take into account a great deal of useful information provided by users (node attributes). In order to surmount this shortcoming, we propose a framework to be utilized in different network with different attributes. We propel some Biased Random Walks (BRW) to find their path from start point to an initially unknown end point with respect to initial energy of start node and energy loss of nodes on the path. We extract structural attribute of networks, using node2vec and compare it with state-of-the-art algorithms and show its accuracy. Then, we extract some content attributes of user and analyze their effect on the results of our algorithm.

Share this page: