Document Theme Extraction Using Named-Entity Recognition

Abstract

The text mining can be implemented by term analysis of word or phrase. This term which describes the concepts of particular sentence is use to define the document theme. The new context-based mining technique is introduced which uses the concept-based mining model to analyze the terms present in sentence, document, and corpus levels. We find the theme of document like organization, medical, entertainment, sport, and so on. Context-based mining apply on statistical data as well as real-time data like Export data from Wikipedia. The theme of document is extracted by using Natural Language processing (NLP) for communication between computer and human languages and name entity recognition (NER) algorithm for identification of entity, entity chunking, and entity extraction. It used to get name entity in text such as person name, organization name, specific locations, time expressions, percentages quantities and so on. NLP and NER are used in context-based mining for finding name of entity and their relationship. Context Vector containing set of documents is used to extract the context of the document. Finally K-Mean algorithm is used for clustering to find inherent groupings of the text documents, then set of clusters are generated where each cluster exhibit high intra cluster similarity and low inter cluster similarity. The text document clustering is used to separate documents into groups or clusters based on their similarity so all groups define the distinct topics.