Terms Visualization for Malay Translated Quran Documents

Abstract

A web-based visualization system is developed to visualize the similarity between root words in Malay translated QuranDocuments. The visualization of terms used is based on their similarities measures using Cosine and Dice coefficients. The degreeof similarity of a term (A) with a processed term (B), can be easily determined by observing the location of term A from term B. Theterm that is located closer to the processed term is considered more similar to the processed term compared to other terms that arelocated farther away. The terms created in the processing of one term can be used as potential queries to search relevant documentsin the Malay translated Quran manually or electronically. The flexibility of this system to visualize different terms will bediscussed. The development of the system involves two stages. The first stage is the processing of 6236 documents of the Malaytranslated Quran to create a database of all terms. The second stage is the creation of the web-based system using the preprocessingdata created in the first stage. Both stages are explored. The visualization will help to improve the understanding of relationshipbetween the terms in this specific domain.