Deep Learning Techniques for Automation and Industrial Applications

12Review of State-of-Art Techniques for Political Polarization from Social Media Network

Akshita Bhatnagar^* and B.K. Sharma

Mandsaur University, Mandsaur, India

Abstract

The nature and scope of online communication have changed as a result of more social networking platforms. The social network has drawn a lot of attention in the last 10 years. The cost of using the internet and Web 2.0 apps to access social networking sites, like Twitter, Facebook, LinkedIn, and Google+, is declining. People are using social networks more and more to get information, news, and opinions on a variety of topics. Everyone will become increasingly aware of how social media is impacting our lives. In social science, the term “group polarization” describes a group’s tendency to take positions that are more extreme than those taken by its members alone. Political science is the social process that divides society into two groups with opponents who have different goals, viewpoints, and attitudes; few participants are neutral or hold an intermediate opinion. The political polarization that characterizes our period has thus attracted a lot of attention from academics and journalists in recent days. Oftentimes, deep learning involves unsupervised, well-controlled contrast learning. For machines to learn or compute independently of humans, we examine several deep learning approaches, such as convolutional neural networks (CNN), recurrent neural networks (RNN), an autoencoder (AE), restricted Boltzmann ...