How Much Noise in Text is too Much: A Study in Automatic Document Classification

Noise is a stark reality in real life data. Especially in the domain of text analytics it has a significant impact as data cleaning forms a very large part (upto 80% time) of the data processing cycle. Noisy unstructured text is common in informal settings such as on-line chat, SMS, email, newsgroups and blogs, automatically transcribed text from speech data, and automatically recognized text from printed or handwritten material. Gigabytes of such data is being generated everyday on the Internet, in contact centers, and on mobile phones. Researchers have looked at various text mining issues such as pre-processing and cleaning noisy text, information extraction, rule learning, and classification for noisy text. This paper focuses on the issues faced by automatic text classifiers in analyzing noisy documents coming from various sources. The goal of this paper is to bring out and study the effect of different kinds of noise on automatic text classification. Does the nature of such text warrant moving beyond traditional text classification techniques? We present detailed experimental results on simulated noise on benchmark datasets viz. Reuters-21578 and 20-newsgroups. We also present interesting results on real life noisy datasets from various contact center domains.