Cluster-Specific Rule Mining for Argumentation-Based Classification

We present a multi-step classification approach that combines classical machine learning methods with computational models for argumentation. In the first step, the dataset is divided into different groups using a clustering algorithm. In the second step, we employ rule-learning algorithms to extract frequent patterns and rules from each resulting cluster. In the last step, we interpret the rules as the input for structured argumentation approaches. Given a new observation, we first assign it to one of the previously generated clusters. Subsequently, the classification of the observation is determined by formulating arguments based on the respective cluster-specific rules for the different classes. Finally, the justification status of the arguments is determined using the argumentative inference method of the structured argumentation approach.