23-08-2012, 11:24 AM
Emotion Argumentation
Emotion.docx (Size: 61.29 KB / Downloads: 120)
Abstract
Argumentation that constitutes a major component of human intelligence is the process by which arguments are constructed and handled. Argumentation is a collection of propositions, all of which are premises except, at most one, which is a conclusion. If we consider the context of emotions, emotion argumentation means to examine the consistency of emotions from a set of premises to its corresponding conclusion. In the present task, we have prepared a baseline system for rule based followed by machine learning frame work, respectively on two types of corpora, ECHR (European Court of Human Rights) and the Araucaria Database. We use the Naïve Baye’s, SMO and Decision Tree classifiers for evaluation the machine learning frame work. We evaluated the results of rule based frame work by manual experts. We used the Bayes’ theorem to find the emotional effect in generating the conclusion from the set of premises using the notion of argumentation.
Introduction
Argumentation is defined as a process whereby arguments are constructed, exchanged and evaluated in light of their interactions with other arguments, each of which comprises a set of premises, pieces of evidence, offered in support of a claim (Michael and Moens, 2009). The claim is a proposition, an idea which is either true or false, put forward by somebody as true. The claim of an argument is normally called its conclusion. Argumentation may also involve chains of reasoning, where claims are used as premises for deriving further claims. An argument is a set of propositions, all of which are premises except, at most, one, which is a conclusion. Any argument follows an argumentation scheme, where the critical questions can be implicit or explicit. Many fields have shown interest in argumentation, e.g. philosophy, logic, psychology or more recently artificial intelligence.
Related Research
Argumentation has not received a great deal of attention in computational linguistics, although it has been a topic of interest for many years. Many fields have shown interest in argumentation, e.g. philosophy, logic, psychology or more recently artificial intelligence. Regarding logics the theories have been divided into two branches: formal logic
and informal logic. Formal logic is the study of inference with purely formal content. An inference possesses a purely formal content if it can be expressed as a particular application of a wholly abstract rule, that is, a rule that is not about any particular thing or property. The works of Aristotle contain the earliest known formal study of logic.
System Frame work
Our ultimate goal is to find premise(s) and conclusion from the argumentation text. Conclusion and premise(s) are determined in ECHR dataset and Araucaria Database by using rule based and machine learning approaches respectively.
If the detection of the argumentative propositions of a text is possible, then it seems that the classification of these propositions by their argumentative function should also be feasible. Following our formalism, we have studied the classification between premises and conclusions. Our approach is again to work with statistical classifiers. We use three classifiers, a Naive Bayes, Sequential Minimal Optimization (SMO) and Decision table (see section 6) for classifying each argumentative clause found into a premise or conclusion. Here, we use more sophisticated features (see Table 1).
Conclusion
All Research on Emotion argumentation is still limited and leaves many interesting challenges. However, to find premises and conclusion using machine learning methods, our system produces good results. In our feature task we are planning to construct enthymemes using schemes and resolution principle of functional logic. Additionally, we are planning to include enthymemes for improving the performance of the system in generating conclusion using premises.