Document Search in Information Retrieval System Using Vector Space Model

Abstract

The current pandemic has spread everywhere. Various effects of pressure in the economic, educational, and social sectors are forced to adjust. So that people really need information about efforts to prevent the spread is very necessary. Search Engine is a program that is used as a tool to find more information on the internet. Search Engine is one of the discussions in the field of Information Retrieval. This system is a document search of unstructured properties. Thus, being able to provide the information needs of a large set of documents (on a local computer server or the internet). The vector space model is one of the many models in Information Retrieval that is used to get the distance and direction between keywords and documents by representing them into vectors. Then the results of ranking using cosine similarity with a dataset of 90 articles about covid19 along with 4 keywords will be tested with precision, recall, and accuracy calculations. The results of the precision calculation get a value of 60% - 73%, recall gets a value for each of the keywords 81%-100% and gets an accuracy value of 85% -89%. The results of these experiments indicate that information retrieval with vector space model is effective with good and stable performance used for information retrieval.