Analysis of Text Mining Tools in Disease Prediction

Abstract

Due to rapid creation of digital data by Internet of Things devices or smart devices, many new modern mining strategies/techniques require to handle/analyse this large amount of data. Note that more than 90% of today’s data is in present (generated) unstructured or semi-structured data format (most of part of this data is being generated only in the past decade). The discovery of appropriate patterns and trends to analyse the text documents from this large big data (i.e., large volume of data) is a big issue. Text mining is a process of extracting interesting and non- trivial patterns from huge amount of text documents. There exist different techniques and tools to mine the text (also other data format) and discover valuable information for future prediction and decision making process. Basically, there are two terms used in making or extracting some relevant information from a data-set, i.e., prediction modelling, and text mining. Predictive models are often used to detect crimes and identify suspects, after the crime has taken place/to detect an email, how likely that it is spam. Similarly, text mining used in applications like digital libraries, academic research field, life science, social media, business intelligence, etc. Today’s different text mining techniques are available for analysing the text patterns and their mining process, some of them are included here as: document classification (text classification, document standardization), information retrieval (keyword search/querying and indexing), document clustering (phrase clustering), natural language processing (spelling correction, lemmatization, grammatical parsing, and word sense disambiguation), information extraction (relationship extraction/link analysis), and web mining (web link analysis), etc.