Predicting and characterising persuasion strategies in misinformation content over social media based on the multi-label classification approach

Persuasion aims at affecting the audience’s attitude and behaviour through a series of messages containing persuasion strategies. In the context of misinformation spread, identifying the persuasion strategies is important in order to warn people to be aware of the analogous persuasion attempts in the future. In this work, we address the prediction of persuasion strategies in micro-blogging posts through a multi-label classification approach based on a variety of lexical and semantic features. We conduct our experiments using a set of well-known multi-label classification algorithms, including multi-label decision tree, multi-label k-nearest neighbours, multi-label random forest, binary relevance and classifier chains. The results show that the model incorporating classifier chains and XGBoost algorithm achieves the best subset accuracy of 0.779 and the highest macro F₁-score of 0.847. In addition, we evaluated and compared the features’ importance for different persuasion strategies and analysed the major errors of miss-out prediction. The findings of this article provide a benchmark for the multi-label classification of persuasion strategies in micro-blogging posts and lead to a better understanding of different persuasion attempts contained in social media misinformation.