STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Artificial Intelligence Research & Advances

Efficient Classification of Noisy Text

  1. Mita K. Dalal

Abstract

Textual content comprises a significant volume of data generated online on a daily basis. The web-generated data often consists of high levels of noise due to a variety of factors.  Development of efficient systems for automatic classification of noisy data is a crucial task in text mining. This paper examines a technique for classification of noisy text which is based on multiple feature selection and supervised learning. The main aim of the paper is to examine the efficiency of the text classification approach against increasing levels of word error rate, using both standard and web-based data sets.  Empirical evaluation of the classification approach indicates that it is efficient and reliable in the presence of noise.

Keywords

Support