Acceleration of Naive-Bayes algorithm on multicore processor for massive text classification

Naive-Bayes algorithm acts as a key baseline of massive text classification, which is widely used in fields of detecting spam, online marketing and so on. Multicore processor is a suitable platform to implement Naive-Bayes because of its flexibility, high performance, and energy-efficiency. This paper proposes a new hopscotch hash scheme to improve the performance of data storing and indexing of Naive-Bayes algorithm, and presents a software implementation of Naive-Bayes text classification mapped in Topo-MapReduce model on a multicore processor with circuit switching and packet switching. Experimental results show that the improved hopscotch hash speeds up by 33% at maximum compared to the original hash, and the proposed Topo-MapReduce speeds up the Naive-Bayes algorithm by 29% at maximum compared to the original MapReduce.