A COMPARISON OF MULTI-LABEL CLASSIFICATION METHODS USING MEKA ON BENCHMARK DATASETS

Kavitha C.R, Mahalekshmi T

Abstract: Recent research interest of many researchers is multi- label classification, where each instance is assigned a set of multiple class labels simultaneously. It is used to solve problems in different application domains such as text categorization, semantic scene classification, music categorization and protein function classification. This paper gives an overview of multi-label classification and its methods. This paper also presents a comparative analysis of multi-label classification methods using MEKA on various data sets such as Genbase and Enron.

Keywords: Machine learning, Classification, Multi-Label Classification, MEKA, Binary Relevance (BR)

DOI: https://doi.org/10.15623/ijret.2016.0509050