Finn, SamanthaMustafaraj, Eni2018-01-082018-01-0820132013https://dl.gi.de/handle/20.500.12116/11332When analysing social media conversations, in search of the public opinion about an unfolding political event that is being discussed in real-time (e.g., presidential debates, major speeches, etc.), it is important to distinguish between two groups of participants: political activists and the general public. To address this problem, we propose a supervised machine-learning approach, which uses inexpensively acquired labeled data from mono-thematic Twitter accounts to learn a binary classifier for the labels “political activist” and “general public”. While the classifier has a 92 % accuracy on individual tweets, when applied to the last 200 tweets from accounts of a set of 1000 Twitter users, it classifies accounts with a 97 % accuracy. Our work demonstrates that machine learning algorithms can play a critical role in improving the quality of social media analytics and understanding, whose importance is increasing as social media adoption becomes widespread.Machine learningPolitical discourseSocial mediaTwitterText/Journal Article1610-1987