COMPARATIVE STUDY OF WORDNET PATH SIMILARITY AND WU-PALMER SIMILARITY FOR ANALYZING TEXT SIMILARITY (CASE STUDIES: THE ENGLISH TRANSLATIONS OF THE QURAN AND AN-NAWAWI'S NARRATED FORTY HADITH)

Muhammad Raffiudin, NIM.: 16650041 (2020) COMPARATIVE STUDY OF WORDNET PATH SIMILARITY AND WU-PALMER SIMILARITY FOR ANALYZING TEXT SIMILARITY (CASE STUDIES: THE ENGLISH TRANSLATIONS OF THE QURAN AND AN-NAWAWI'S NARRATED FORTY HADITH). Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (COMPARATIVE STUDY OF WORDNET PATH SIMILARITY AND WU-PALMER SIMILARITY FOR ANALYZING TEXT SIMILARITY (CASE STUDIES: THE ENGLISH TRANSLATIONS OF THE QURAN AND AN-NAWAWI'S NARRATED FORTY HADITH)) 16650041_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (4MB) | Preview
	Text (COMPARATIVE STUDY OF WORDNET PATH SIMILARITY AND WU-PALMER SIMILARITY FOR ANALYZING TEXT SIMILARITY (CASE STUDIES: THE ENGLISH TRANSLATIONS OF THE QURAN AND AN-NAWAWI'S NARRATED FORTY HADITH)) 16650041_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (5MB) | Request a copy

Abstract

Studying the Quran and the Hadith side by side can help us understand that the two are fundamental and two main resource and essential wellspring of Islamic knowledge and law, which manages muslim the genuine information and are fundamental needs of their everyday life. There are many debates about similarities between those holy scriptures from many famous preachers and scholars. Technology, as an application of science, can be used as an alternative solution to solve these problems. There is important to stress that this research is not a religious study. There are at least two overall approaches to determine textsimilarity; the vector space model and semantic similarity —define the similarity or the distance. The similarity between words is often represented by a similarity between concepts associated with the words. The objective of this study to answer the statement that this research aims to analyzing data sets from both of the Quran and the Hadith using WordNet path similarity and Wu-Palmer similarity to find semantic similarities between each sentences from both the Quran and the Hadith and compare both of the method. The result from implementation of both method, it can be concluded that the use of the WordNet path similarity and Wu-Palmer to the Quran Sahih International Translation with the The An-Nawawi Forty Hadith Translation and using 0.8 as threshold for similarity value for each pairs produces 0.1% similar pairs for path similarity and 0.2% for Wu-Palmer similarity from the 1.319.995 datasets run which is a combination of pairs of sentences taken from all verses from both scriptures. This method also evaluated and have acceptable accuracy. By using 0.8 as threshold for similarity value, it shows 0.583% accuracy when using path similarity and 0.654% while using Wu-Palmer similarity, using 0.85 as threshold shows 0. 519% accuracy when using path similarity and 0.607% while using Wu-Palmer similarity, using 0.9 as threshold shows 0.436% accuracy when using path similarity and 0.513% while using Wu-Palmer similarity, using 0.95 as threshold shows 0.369% accuracy when using path similarity and 0.399% while using WuPalmer similarity. Despite both of the method is success to identify similarity between two sentences, but they have slighty different accuracy and Wu-Palmer similarity is superior than path similarity when identifiying sentences between Quran Sahih International Translation and An-Nawawi Forty Hadith Translation. Looking ahead, we might be able to improve our results by using multipliers such as reverse document frequency (TF-IDF), combining the results of several steps in WordNet similarity, using vector space models and optimal matching methods.

Share this knowledge with your friends :

Actions (login required)

View Item