Abstract: A new multi-label text classification algorithm based on hyper ellipsoidal was proposed in this paper. For every class, the smallest hyper ellipsoidal that contains the samples of the class is structured, which can divide the class samples from others. For the sample to be classified, its class is confirmed by the hyper ellipsoidal that surrounds it. If the sample is not surrounded by any hyper ellipsoidal, the membership is used to confirmed its class. The experiments were done on Reuters 21578 and the experiment results show that the algorithm has a higher performance on classificalion speed and classification precision compare with hyper sphere algorithm.

Key words: Hyper ellipsoidal, Multi-label classification, Extension factor, Membership