Modelling argumentation in short text: A case of social media debate

The technological leaps of artificial intelligence (AI) and the rise of machine learning have triggered significant progress in a plethora of natural language processing (NLP) and natural language understanding tasks. One of these tasks is argumentation mining which has received significant interest in recent years and is regarded as a key domain for future decision-making systems, behaviour modelling, and natural language understanding problems. Until recently, natural language modelling tasks, such as computational argumentation schemes, were often tested in controlled environments, such as persuasive essays, reducing unexpected behaviours that could occur in real-life settings, like a public debate on social media. Additionally, the growing demand for enhancing the trust and the explainability of the AI services has dictated the design and adoption of modelling schemes to increase the confidence in the outcomes of the AI solutions. This paper attempts to explore modelling argumentation in short text and proposes a novel framework for argumentation detection under the name Abstract Framework for Argumentation Detection (AFAD). Moreover, different proof-of-concept implementations are provided to examine the applicability of the proposed framework to very short text developing a rule-based mechanism and compare the results with data-driven solutions. Eventually, a combination of the deployed methods is applied increasing the correct predictions in the minority class on an imbalanced dataset. The findings suggest that the modelling process provides solid grounds for technical research while the hybrid solutions have the potential to be applied to a wide range of NLP-related tasks offering a deeper understanding of human language and reasoning.