During the 2016 US elections Twitter experienced unprecedented levels of propaganda and fake news through the collaboration of bots and hired persons, the ramifications of which are still being debated. This work proposes an approach to identify the presence of organized behavior in tweets. The Random Forest, Support Vector Machine, and Logistic Regression algorithms are each used to train a model with a data set of 850 records consisting of 299 features extracted from tweets gathered during the 2016 US presidential election. The features represent user and temporal synchronization characteristics to capture coordinated behavior. These models are trained to classify tweet sets among the categories: organic vs organized, political vs nonpolitical, and pro-Trump vs pro-Hillary vs neither. The random forest algorithm performs better with greater than 95% average accuracy and f-measure scores for each category. The most valuable features for classification are identified as user based features, with media use and marking tweets as favorite to be the most dominant.

The successful use of social media to manipulate public opinion via bots and hired individuals to spread (mis)information to unsuspecting users reached alarming levels due to the manipulations during the 2016 US elections and the Brexit deliberations in the UK. Fake interaction such as “liking” and “retweeting” are staged to foster trust in the posts of bots and individuals, which makes it difficult for individuals to detect the posts that are part of greater schemes. We propose an approach based on supervised learning to classify collections of tweets as “organized” when they inhabit premeditated intent and as “organic” otherwise. Features related to users and posting behavior are used to train the classifiers using 851 data sets totaling above 270 million tweets. Further classifiers are trained to assess the effectiveness of the selected features. The random forest algorithm persistently yielded the best results with scores greater than 95% for both accuracy and f-measure. For comparison purposes, unsupervised learning methods were used to cluster the same data sets. The Gaussian Mixture Model clustered [organized vs organic] data set with 99% agreement with the labels. The success of using only behavioral features to detect organized behavior is encouraging.

No abstract