Semantic subspace learning for text classification using hybrid intelligent techniques

Abstract

A vast data repository such as the web contains many broad domains of data which are quite distinct from each other e.g. medicine, education, sports and politics. Each of these domains constitutes a subspace of the data within which the documents are similar to each other but quite distinct from the documents in another subspace. The data within these domains is frequently further divided into many subcategories. In this paper we present a novel hybrid parallel architecture using different types of classifiers trained on different subspaces to improve text classification within these subspaces. The classifier to be used on a particular input and the relevant feature subset to be extracted is determined dynamically by using maximum significance values. We use the conditional significance vector representation which enhances the distinction between classes within the subspace. We further compare the performance of our hybrid architecture with that of a single classifier-full data space learning system and show that it outperforms the single classifier system by a large margin when tested with a variety of hybrid combinations on two different corpora. Our results show that subspace classification accuracy is boosted and learning time reduced significantly with this new hybrid architecture.

Phylogenetic and Biological Significance of Evolutionary Elements from Metazoan Mitochondrial Genomes

“…In document classification, the highest priority is to find relevant information, particularly in electronic documents [71] . Several studies have discussed how to effectively and automatically classify documents into separate classes [72] . As with document classification, broad key K-strings have helped classify studies into different styles [46] , [72] , e.g., literature and natural science, whereas specific key K-strings have played different roles such as subdividing studies into different subjects of the same style, for example, classifying mathematics and biology as two divisions of natural science.…”

“…Several studies have discussed how to effectively and automatically classify documents into separate classes [72] . As with document classification, broad key K-strings have helped classify studies into different styles [46] , [72] , e.g., literature and natural science, whereas specific key K-strings have played different roles such as subdividing studies into different subjects of the same style, for example, classifying mathematics and biology as two divisions of natural science. Therefore, we suggest using broad key K-strings to allocate species into phyla and phylum-specific key K-strings to classify species belonging to the same phylum.…”

Efficient E-Mail Spam Detection Strategy Using Genetic Decision Tree Processing with NLP Features

“…Here, the headlines of Reuters Corpus are used, since it provides a short summary of each article. A single Reuters Corpus headline includes a single line of text data with 3 to 12 words [ 11 ]. For text classification in documents, a general and special case of a Hy-RNC is explored due to its potential in TC.…”

“…The data in the domain are divided into many categories. The subspaces of data within the domain are processed as independent objects [ 11 ]. Researchers make use of web as a source of collecting information.…”