Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Jurnal Sistem Informasi

PENYUSUNAN STRONG’S CONCORDANCE UNTUK ALKITAB PERJANJIAN BARU BAHASA INDONESIA . Gunawan; Devi Dwi Purwanto; Herman Budianto; Indra Maryati
Jurnal Sistem Informasi Vol. 5 No. 2 (2009): Jurnal Sistem Informasi (Journal of Information System)
Publisher : Faculty of Computer Science Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1024.99 KB) | DOI: 10.21609/jsi.v5i2.265

Abstract

Sampai saat ini belum pernah ditemukan Alkitab Perjanjian Baru Bahasa Indonesia secara online yang dilengkapi dengan Strong’s Concordance. Oleh karena itu penelitian ini melakukan penyusunan Strong’s Concordance ke dalam Alkitab Perjanjian Baru Bahasa Indonesia. Penyusunan Strong’s Concordance dilakukan dengan menggunakan pedoman teori yang ada pada Natural Language Processing (NLP) dan teori Web Mining. Penyusunan nomor strong tersebut dimulai dengan melakukan pendekatan nomor strong berdasarkan kemunculan katanya. Kemudian pada tahap selanjutnya digunakan pendekatan alignment antara kata yang ada pada Alkitab Bahasa Indonesia dengan nomor strong yang terdapat pada Alkitab Bahasa Inggris dengan menggunakan word alignment. Pendekatan ketiga menggunakan pendekatan n-gram dengan perhitungan mutual information untuk mencari arti kata yang terdiri lebih dari satu kata. Pendekatan keempat dilakukan dengan cara melakukan stemming pada corpus Alkitab Perjanjian Baru Bahasa Indonesia yang mana nantinya digunakan sebagai corpus baru untuk melakukan pencarian pada tahap satu sampai dengan tahap tiga. Dilakukan juga pendekatan lain seperti pencarian proper name, pencarian nomor strong yang hanya memiliki satu frekuensi dan pendataan nomor strong yang termasuk dalam conjuction, preposition, dan pronoun. Hasil penelitian adalah adanya Alkitab Perjanjian Baru Bahasa Indonesia yang dilengkapi dengan nomor strong, pembelajaran Alkitab menjadi lebih mudah. Until now have not found a New Bible Testamen in Bahasa online which is equipped with a Strong's Concordance. Therefore, this study prepare a Strong's Concordance to the New Bible Testament Indonesian. Preparation of Strong's Concordance is done using the existing guidelines on the theory of Natural Language Processing (NLP) and the theory of Web Mining. The preparation of these strong numbers begins with based on the word strong numbers aproach. Then on the next phase alignment approach between existing words in the Bible Bahasa with strong numbers contained in the English Bible using the word alignment. The third approach uses n-gram approach with the calculation of mutual information to find the meaning of words consisting in more than one word. The fourth approach is performed by stemming the New Bible Testament corpus Bahasa which will be used as a new corpus to perform a search in stage one up to stage three. There is also another approach such as the proper name search, the search for strong numbers that have only one frequency, and data collection that included strong numbers in conjuction, preposition, and pronoun. The result is the New Bible Testament Bahasa which comes with a number of strong more easier to learn.
SINONIM DAN WORD SENSE DISAMBIGUATION UNTUK MELENGKAPI DETEKTOR PLAGIAT DOKUMEN TUGAS AKHIR Devi Dwi Purwanto
Jurnal Sistem Informasi Vol. 11 No. 1 (2015): Jurnal Sistem Informasi (Journal of Information System)
Publisher : Faculty of Computer Science Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1492.018 KB) | DOI: 10.21609/jsi.v11i1.412

Abstract

Plagiarism can be categorized into several levels: carbon copy, the addition of words, word substitutions, changing active into passive sentences, and paraphrase. In this research, the detection is only performed by local similarity assessment method. This research is categorized into 3 major processes: preprocessing, candidate determination, and calculation of similarity. In preprocessing, extraction and conversion of a PDF file into XML is performed. Stopword removal and stemming are also performed in this process. For Candidates determination, the process used VSM (Vector Space Model) algorithm using Lucene.NET. It will then calculate the similarity values of the candidates. Similarity values that meet the threshold will be processed in the third stage. The next process is detecting plagiarism at the level of carbon copy. The plagiarism of the substitution level will be determined by finding synonymous with Lesk algorithm and utilizing WordNet as a language dictionary. Lesk notice the words around it, before doing the search process is synonymous with Lesk, performed first sentence extractor. From this experiment, it is concluded that the determination of synonyms using WordNet and Lesk algorithm does not seem to increase its similarity value role. This is due to the difficulty of finding plagiarism by just substituting words. However, plagiarism at the level of carbon copy can be handled with the help of sentence matching.