Argumentation is the discipline that studies the way in which humans debate and articulate their opinions and beliefs. Argumentation mining is a research area at the cross-road of many fields, such as computational linguistics, machine learning, artificial intelligence, natural-language processing. The main goal of argumentation mining is the automatically extraction and identification of arguments and their relations from natural language text documents.
This very complex problem requires dealing with a variety of interwined sub-tasks, which can be addressed either jointly, or following a pipeline scheme. The two fundamental tasks are the detection of argument components, and the prediction of their relations. Among the many approaches developed in recent years for argumentation mining, based on advanced machine learning and natural language processing techniques, the vast majority is genre-dependent, or domain-dependent, as they exploit information that is highly specific of the application scenario.
Argumentation mining can be considered as an evolution of sentiment analysis: the goal of opinion mining is to understand what people think about something, the aim of argumentation mining is to understand why. For this reason argumentation has been proposed in applications that include improving information retrieval and information extraction as well as end-user visualization and summarization of arguments.