A Multi-label Classification Framework Using the Covering Based Decision Table.

Multi-label classification (MLC) has recently drawn much attention thanks to its usefulness and omnipresence in real-world applications, in which objects may be characterized by more than one labels. One of the challenges in MLCis to determine the relationship between the labels due to the fact that there is not any assumptions of the independence between labels, and there is not any information and knowledge about these relationships in a training dataset. Recently, many researches have focused on exploiting these label relationships to enhance the performance of the classification, however there have not many of them using the covering rough set. This paper propose a multi-label classification algorithm named CDTML, based on ML-KNN algorithm, using covering based decision table which exploits the relationship between labels to enhance the performance of the multi-label classifier. The experimental results on serveral dataset of Enron, Medical and a Vietnamese dataset of hotel reviews shown the effectiveness of the proposed algorithm.