Online social media is a popular research topic for both computer and social scientists as it can be investigated with robust analytic tools and reflects a certain slice of the mass behavior of society. It is interesting to question whether the actors of politics try to exploit the opportunities provided by online social media. The manipulators attempt to influence the opinions of readers participating in political debates within social networks. The question is how the manipulators can be detected using the published material.

The paper develops a method for discerning collaborative efforts in a political discussion. For this purpose, 64 attributes of published texts are selected, and are later reduced to a smaller subset to distinguish between manipulators and non-manipulators in a more efficient way. Using machine learning and data mining technologies, a detection method is devised and implemented. As a proof of concept, a large data set from Korean social media is used for validating the proposed method.

The paper meticulously describes the applied numerical parameters to compute statistical values that can be interpreted for classification purposes. The services of an open-source data mining package (Weka) are used for classifying the actors of political discussions. A comparison with existing methods is carried out to analyze the compliance of the proposed method for the claimed purpose.

The paper is worth reading for researchers working on social media networks or investigating political manipulation.