A Concise Survey on Text Data Mining

Abstract: In recent days the use of internet is growing rapidly. The data used and shared by the users on internet is in huge amount which is available in unstructured, semi- structured and structured form such as images, texts, audios or videos. For analysis and processing of such immense data, data mining came into picture. Data mining is the process of retrieving previously unknown and significant information from given set of data. Among the data available in digital form over the internet, 85% of data available is in unstructured form. Most of the data used is in text form such as Electronic mail, Internet chat, World Wide Web, Digital libraries, Electronic Publications, and Technical reports etc. For the purpose of knowledge discovery and information retrieval from such textual data text mining is used. Text mining is a kind of data mining technique responsible for retrieving valuable information from collection of text. In this paper, focus is on concept of text mining, text mining process flow, data mining methods used in text mining such as Clustering, Topic detection, Information Extraction and Natural Language Processing. Also presenting some real world applications of text mining.

Keywords: Unstructured Data, Semi-structured Data, Structured Data, Data mining, Natural Language Processing (NLP), Information Extraction (IE).