Submit your paper : editorIJETjournal@gmail.com

Paper Title : Information Retrieval on Hadith Sahih Bukhari Using Vector Space Model Method and Expansion Query

ISSN : 2395-1303
Year of Publication : 2022
10.29126/23951303/IJET-V8I1P14

Authors: Dede Irawan, Imam Halim Mursyidin, Doni Prasetyo

         


Abstract
According to the big Indonesian dictionary the hadiths are words, deeds, takrir (decrees) of the Prophet Muhammad sallallaahu ‘alayhi wa sallam. narrated or told by friends to explain and establish Islamic law. There are many hadith narrators who become a reference for Muslims, some of them are Muslim Imam, Imam Ahmad and Imam Bukhari. For Muslims, Shahih Bukhari is the main reference to deepen As-Sunnah as the second source of Islamic law after the Koran. As the development of digital technology, Hadith is packaged into digital form. Currently the Hadith can be read through computers, smartphones and other digital devices. On the smartphone there is a Hadith Sahih Bukhari v.3.6 application created by Islamic Developers. The Hadith application has a search feature but the search results are still less relevant. Searching can only be done if the keyword phrase (Query) entered exactly matches the phrase in the digital text document in Indonesian. This is because the search is still conventional. For example, we tried to find hadiths with the keyword "usury" but in the search results the keyword "geriba" also appeared so it does not match what we are looking for. The problem that occurs is that of the many hadith narrated by Imam Bukhari, the author is difficult to find relevant traditions in accordance with the search. Therefore we need an Information Retrieval to support the search, to make an Information Retrieval the writer will use the Vector Space Model and Expansion Query methods. The combination of these methods is expected to provide relevant hadith information in accordance with the search.

Reference
[1] Adisantoso, J., Ridha, A. dan Agusetyawan, A. W. (2002) “RELEVANCE FEEDBACK PADA TEMU-KEMBALI TEKS BERBAHASA INDONESIA DENGAN METODE IDE-DEC-HI DAN IDE-REGULAR,” hal. 1–8. [2] Alfian Sukma1, Badrus Zaman, E. P. (2002) “Klasifikafi Dokumen Temu Kembali Informasi dengan K-Nearest Neghbour Information Retrieval Document Classified with K-Nearest Neighbor,” Mycological Research, 106(11), hal. 1323–1330. [3] Amin, F. (2012) “Sistem Temu Kembali Informasi dengan Metode Vector Space Model,” Jurnal Sistem Informasi Bisnis, 2(2), hal. 78–83. doi: 10.21456/vol2iss2pp078-083. [4] Az-zabidi (2016) “Mukhtasar Shahih Bukhari.” Diedit oleh Ummul Qura. 2016.Baeza-Yates, R. dan Ribeiro-Neto, B. (1999) “Modern Information System. Pearson in.” Boston. USA: Eddison Wesley (1718). [5] Hidayat, W. (2013) “Indexing and Retrieval Engine untuk Dokumen Berbahasa Indonesia dengan Menggunakan Inverted Index,” Seminar Nasional Informatika dan Aplikasinya (SNIA) 2015, (October). Tersedia pada: https://www.researchgate.net/publication/2844927 48. [6] Karyono, G., Utomo, F. S., Sistem, A. dan Balik, T. (2012) “Temu Balik Informasi Pada Dokumen Teks Berbahasa Indonesia Dengan Metode Vector Space Retrieval Model,” Seminar Nasional Teknologi Informasi dan Terapan 2012, 2012(Semantik), hal. 282–289. [7] Kent, A. (1971) “Information Analysis and Retrieval. 3rd Editio.” New York: Becker and Heys. [8] Lancaster, F. W. (1979) “Information Retrieval System: Characteristics, Testing, and Evaluation. 2nd Editio.” Diedit oleh J. Wiley. New York. [9] Lubis, J. H. (2017) “Analisa Performansi Query Pada Database Smell,” Jurnal Manajemen dan Informatika Pelita Nusantara, 21(1), hal. 42–49. [10] Monica, M., Winarno, W. W. dan Sunyoto, A. (2016) “Information Retrieval Dokumen Tesis Untuk Mengetahui Kemiripan dengan Penelitian Yang Telah Ada,” Jurnal Transformasi, 12(2), hal. 105–115. [11] Nurul Justina Mahardianingroem, A. S. (2018) “PENERAPAN KAMUS DASAR PADA ALGORITMA PORTER UNTUK MENGURANGI KESALAHAN STEMMING BAHASA INDONESIA,” 10(2), hal. 103–112. [12] Pamungkas, Z. Y. dan Ridok, A. (2015) “QUERY EXPANSION PADA SISTEM TEMU KEMBALI INFORMASI DOKUMEN BERBAHASA INDONESIA MENGGUNAKAN PSEUDO RELEVANCE FEEDBACK Studi kasus: Perpustakaan Universitas Brawijaya.” [13] Salton, G. (1989) “Automatic Text Processing: TheTransformation, Analysis, and Retrieval of Information by Computer.” USA: Addison-Wesley Longman Publishing Co., Inc. [14] Sanjaya, A. (2016) “OPTIMASI QUERY UNTUK PENCARIAN DATA MENGGUNAKAN PENGURAIAN KALIMAT,” hal. 6–7. [15] Wibowo, A. (2012) “Peningkatan Performasi Sistem Temu Balik Informasi dengan Metode Phrasal Translation dan Query Expansion,” Batam: Politeknik Negeri Batam. Tersedia pada: https://scholar.google.com/citations?user=QB4WJ b4AAAAJ&hl=en#d=gs_md_citad&u=%2Fcitations%3Fview_op%3Dview_citation %26hl%3Den%26user%3DQB4WJb4AAAAJ%26 citation_for_view%3DQB4WJb4AAAAJ%3A9yK SN-GCB0IC%26tzom%3D-420. [16] Zain, M. Y. dan Suswati (2016) “Information Retrieval System Pada Pencarian File Dokumen Berbasis Teks Dengan Metode Vector Space Model Dan Algoritma ECS Stemmer,” Jurnal Insand Comtech, 1(1), hal. 30–37
Keywords
-Pseudo Relevance Feedback, Hadis Online, Cosine Similarity