Decision tree learning with fuzzy labels

Label semantics is a random set based framework for "Computing with Words" that captures the idea of computation on linguistic terms rather than numerical quantities. Within this new framework, a decision tree learning model is proposed where nodes are linguistic descriptions of variables and leaves are sets of appropriate labels. In such decision trees, the probability estimates for branches across the whole tree is used for classification, instead of the majority class of the single branch into which the examples fall. By empirical experiments on real-world datasets it is verified that our algorithm has better or equivalent classification accuracy compared to three well known machine learning algorithms. By applying a new forward branch merging algorithm, the complexity of the tree can be greatly reduced without significant loss of accuracy. Finally, a linguistic interpretation of trees and classification with linguistic constraints are introduced.