Title: Application of Automatic Indonesian Thesaurus Development using Statistics - Based Theory

Year of Publication: Sep - 2015
Page Numbers: 51-58
Authors: Mira Ziveria
Conference Name: The International Conference on Software Engineering, Mobile Computing and Media Informatics (SEMCMI2015)
- Malaysia

Abstract:


This study builds software named Thesindo (Thesaurus Indonesia Otomatis) or “Automatic Indonesian Thesaurus” which serves search for words in Indonesian semantically associated with a word (flat thesaurus) using statistics-based theory. Thesaurus database will be built automatically by the application using the material number of articles in Indonesian language. The result is a database that contains words that are interrelated. The software development using the System Development Life Cycle (SDLC). The implementation of the software using Borland Delphi 6.0 programming and data storage in SQL Server 2008. The application will be used on the Windows 7 operating system environment specification test specified stating that the software is considered correct if it meets certain test cases in accordance with the specification requirements. Statistical theory can be used to estimate the association said semantically. The software has been made to build a database of Indonesian thesaurus automatically from a collection of articles. Thesindo performance will be better if you use a lot of articles.