DOCUMENT RANKING AND CLASSIFICATION USING COSINE SIMILARITY AND PARAMETER FREE THRESHOLD

Abstract

Information Retrieval is the science of searching information within documents. Documents are in huge quantity and still growing. It is very difficult to find the information according to requirements of user. So different algorithms are being proposed based on long research in information retrieval and data mining. Search Engines are important application of Information Retrieval and programs which are used for effective and efficient retrieval of information as required by the user. Search Engine gives results based on some algorithms to index and rank documents and calculates the similarity of query with the corpus of documents. Vector Space Model are used to index documents with documents represented as vectors and ranking is calculated by Term Frequency/Inverse Document Frequency (TF/IDF) and Cosine Similarity. In this Thesis, Keyword based Search are used for ranking of documents Documents are ranked as required by the user, but there are wide categories of documen...