A NOTE ON INDIAN LANGUAGES TEXT CLASSIFICATION SYSTEMS

Due to the exponential growth of computer and internet users in India, in last two decade, digital content of Indian languages content is rapidly increasing. This has imposed technical challenges of searching, storing and managing this gigantic information. These issues are becoming complex day by day [due to pouring of Indian languages digital content on the net]. Most of these issues can be addressed by neat organization and classification of these contents. Automatic text classification techniques addresses the searching and information management issues by automatically assigning text documents to the predefined classes based on their contents. It is a useful, popular technique that can save labor, money and time problems. This paper aims to discuss the state of Indian languages text classification research by enlisting different research work, their approaches and reported results. The paper begins with preliminary discussion on text classification its applications and process phases, followed by detailed discussion on Indian languages text classification on reported research. Various text classification techniques and results are also discussed. Some of the linguistic issues in the context of text classification are also discussed.