Pencarian Ayat Al-Qur’an Berdasarkan Hasil Transliterasi Menggunakan Algoritma Levenshtein Distance Dengan Metode N-Gram

Daud, Fauzy Widiyatno (2020) Pencarian Ayat Al-Qur’an Berdasarkan Hasil Transliterasi Menggunakan Algoritma Levenshtein Distance Dengan Metode N-Gram. Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

Preview	Text ABSTRACT.pdf - Accepted Version Download (65kB) | Preview
Preview	Text ABSTRAK.pdf - Accepted Version Download (67kB) | Preview
	Text COVER.pdf - Accepted Version Download (3MB)
Preview	Text BAB 1.pdf - Accepted Version Download (80kB) | Preview
Preview	Text BAB 2.pdf - Accepted Version Download (226kB) | Preview
Preview	Text BAB 3.pdf - Accepted Version Download (249kB) | Preview
	Text BAB 4.pdf - Accepted Version Restricted to Registered users only Download (12MB)
Preview	Text BAB 5.pdf - Accepted Version Download (67kB) | Preview
Preview	Text DAFTAR PUSTAKA.pdf - Accepted Version Download (124kB) | Preview
	Text LAMPIRAN.pdf - Accepted Version Restricted to Registered users only Download (1MB)

Abstract

The Qur'an has 114 chapters, 6,236 verses, and 77,439 words. With such a large number, searching for chapters, verses, and words manually is difficult and takes a long time. As technology advances, searching for chapters, verses and words in the Al-Qur'an can be done quickly and easily through modern computing. Of the many Al-Quran applications that exist, there are still deficiencies, especially in the search feature. Among them is the verse search feature which requires the user to type in a search keyword in the form of a verse fragment in Arabic and Arabic script. This is of course an obstacle for users who cannot speak and write Arabic script. There are even applications that don't have a verse search feature so that users who want to do a verse search cannot be done. Search for verses of the Al�Qur'an can be done based on transliteration or script transfer for users who cannot write Arabic characters. The problem that arises in searching based on transliteration is that each user has a different understanding regarding the transliteration of a pronunciation of the Al-Qur'an verse which results in different writing. In this study, the authors built a system to search Al-quran verses using the Levenshtein Distance algorithm with the n-gram method to handle the differences in writing. The Levenshtein Distance algorithm can handle character differences in keywords and data to be searched by calculating the similarity distance value between 2 strings, the smaller the value, the more similar it is. The n-gram method is a method for breaking a text into a series of characters or words. This method can also be used to build an index. System testing was carried out on 4 respondents by entering 40 queries which is sliced verses in surah Al-Fatihah and all of surahs in juz 30. From the testing, the average value of precision was 63.82% and recall 97.77% for bigram, precision 64.5% and recall 99.05% for trigram, and precision 68.95% and recall 81.07% for quintgram. Meanwhile, the average time needed for system to search and display the searching result is 344 milliseconds. Keyword : Levenshtein Distance, N-Gram, Qur’an Verses Searching, Transliteration

Actions (login required)

View Item