Social media, AI, and political affiliation

Twitter is one of the famous micro-blogging websites, currently has 309 million active users. Most famous people, including political leaders, uses Twitter to disseminate information to their followers. People retweet the information shared by the political leaders, which expose their political affiliation to the public. Moreover, this re-sharing could impact the personal and social life of the users. This paper aims to identify the polarity (support/opposition) of the tweets against the current government. For this purpose, a Convolutional Neural Network (CNN) based model is proposed to identify the polarity. We conducted our experiments on 10,000 tweets collected from 60 different political users accounts. Compared to the other techniques with the various hyperparameters configuration, our proposed model outperforms the baseline machine learning models.