ArgMine: Argumentation Mining from Text

Abstract

The aim of argumentation mining is the automatic detection and identification of the argumentative structure contained within a piece of natural language text. An argument is an ancient and well studied rhetorical structure. In a general form, arguments are justifiable positions where pieces of evidence (premises) are offered in support of a conclusion. The ambiguity of natural language text, different writing styles, implicit context and the complexity of building argument structures are some of the challenges which make this task very challenging. By automatically extracting arguments from text, we are able to tell not just what views are being expressed, but also what are the reasons to believe those particular views. Therefore, argumentation mining has the potential to improve some research topics such as opinion mining, recommender systems and multi-agent systems. The full task of argumentation mining can be decomposed into several subtasks. This thesis focuses on the automatic detection and identification of the argumentative components presented in the original text. This involves detecting the zones of text that contain argumentative content and the identification of fragments of text that will form the elementary units of the argument. In order to automatically detect and identify argumentative components in text, supervised machine learning algorithms will be used. The target corpus used to train the algorithms are news written in Portuguese language.