Sigit Purnomo

Sigit Purnomo

Senior Lecturer at Informatics Department, Universitas Atma Jaya Yogyakarta

Development of Typographical Error Identification Application in Indonesian Language Using Jaro-Winkler Distance Algorithm

3 minute read

New publication in collaboration with my undergraduate students, Grelly. This publication is based on her final project to get her bachelor’s degree.

Language: Indonesian

Abstract:
Text is one of the media used by humans to communicate and interact every day, especially in the field of education, for example, in writing a final project report. The most common thing in writing text is typographical errors. Based on these problems, an application is needed to help the writer to be able to identify typographical errors in the Indonesian Language document. The application developed using Laravel version 5.8 for web application and Python version 3 for processing datasets, developing model, and developing web services. Model built uses the NLTK library and Jaro-Winkler distance algorithm implemented using the pylibjaro library. The dataset uses an open-source dataset in the form of a list of words from KBBI. This application only supports pdf files. The results of the model are applied to the web services with output in the form of JSON data. The JSON data contains a list of words that have true or false values, the number of document words, the number of correct words, the number of incorrect words, and the time of program execution.

Keywords: Text, Document, Bahasa Indonesia, Typographical Error, Jaro-Winkler Distance

Fulltext: PDF(Indonesian Language)

DOI: 10.30595/juita.v8i1.6344

References:

[1] A. I. Fahma, I. Cholissodin, and R. S. Perdana, “Identifikasi Kesalahan Penulisan Kata ( Typographical Error ) pada Dokumen Berbahasa Indonesia Menggunakan Metode N-gram dan Levenshtein Distance,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 2, no. 1, pp. 53–62, 2018.

[2] Murtiningsih S.Pd, “Kesalahan Berbahasa Indonesia Mahasiswa S-1 PGSD STIKIP Nuuwar Fak-fak,” J. Penelit. Ilmu Pendidik., vol. 6, no. 1, pp. 74–82, 2013.

[3] M. Javed et al., “A Study of Students’ Assessment in Writing Skills of the English Language,” Int. J. Instr., vol. 6, no. 2, pp. 129–144, 2013.

[4] Y. Rochmawati and R. Kusumaningrum, “Studi Perbandingan Algoritma Pencarian String dalam Metode Approximate String Matching untuk Identifikasi Kesalahan Pengetikan Teks,” J. Buana Inform., vol. 7, no. 2, pp. 125–134, 2016.

[5] K. M. Suryaningrum and A. T, “Pengkoreksian dan Suggestion Word pada Keyword Menggunakan Algoritma Jaro-Winkler,” J. Teknol. Informasi-AITI, vol. 13, no. 2, pp. 169–181, 2016.

[6] J. Frando, I. Ruslianto, R. Hidayati, J. Rekayasa, and S. Komputer, “Penerapan Jaro Winkler Distance dalam Aplikasi Pengoreksi Kesalahan Penulisan Bahasa Indonesia Berbasis Web,” Coding J. Komput. dan Apl., vol. 07, no. 03, pp. 44–53, 2019.

[7] T. Maghfira, I. Cholissodin, and A. Widodo, “Deteksi Kesalahan Ejaan dan Penentuan Rekomendasi Koreksi Kata yang Tepat Pada Dokumen Jurnal JTIIK Menggunakan Dictionary Lookup dan Damerau-Levenshtein Distance,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 1, no. 6, pp. 498–506, 2017.

[8] W. W. A. Umboh, S. R. Sentinuwo, and A. M. Sambul, “Rancang Bangun Aplikasi Deteksi Kesalahan Penulisan Naskah Dokumen Skripsi,” E-Journal Tek. Inform., vol. 11, no. 1, 2017.

[9] C. I. Ratnasari, S. Kusumadewi, and L. Rosita, “A Non-Word Error Spell Checker for Patient Complaints in Bahasa Indonesia,” Int. J. Inf. Technol. Comput. Sci. Open Source, vol. 1, no. 1, pp. 18–21, 2017.

[10] M. M. Yulianto, R. Arifudin, and A. Alamsyah, “Autocomplete and Spell Checking Levenshtein Distance Algorithm To Getting Text Suggest Error Data Searching In Library,” Sci. J. Informatics, vol. 5, no. 1, p. 75, 2018.

[11] P. H. Hema and C. Sunitha, “Spell Checker for Non Word Error Detection : Survey,” Int. J. Adv. Res. Comput. Sci. Softw. Eng., vol. 5, no. 3, pp. 360–363, 2015.

[12] A. Prasetyo, W. M. Baihaqi, and I. S. Had, “Algoritma Jaro-Winkler Distance: Fitur Autocorrect dan Spelling Suggestion pada Penulisan Naskah Bahasa Indonesia di BMS TV,” J. Teknol. Inf. dan Ilmu Komput., vol. 5, no. 4, p. 435, 2018.

[13] H. Gueddah, A. Yousfi, and M. Belkasmi, “The filtered combination of the weighted edit distance and the Jaro-Winkler distance to improve spellchecking Arabic texts,” Proc. IEEE/ACS Int. Conf. Comput. Syst. Appl. AICCSA, vol. 2016-July, no. May 2019, 2016.

[14] Mutammimah, H. Sujaini, and R. D. Nyoto, “Analisis Perbandingan Metode Spelling Corrector Peter Norvig dan Spelling Checker BK-Trees pada Kata Berbahasa Indonesia,” J. Sist. dan Teknol. Inf., vol. 5, no. 1, pp. 1–5, 2016.

[15] R. Gadde and J. Kelly, “Using Multiprocessing to Make Python Code Faster,” Medium, 2018. [Online]. Available: https://medium.com/@urban_institute/using-multiprocessing-to-make-python-code-faster-23ea5ef996ba. [Accessed: 28-Jul-2019].

You may also enjoy

Extraction and attribution of public figures statements for journalism in Indonesia using deep learning

2 minute read

Published:

News articles are usually written by journalists based on statements taken from interviews with public figures. Attribution from such statements provides important information and it can be extracted from news articles to build a knowledge base by developing a sequential tagging scheme such as entity recognition. This research applies two deep learning architectures: recurrent neural networks-based and transformer-based, to establish public figures statement attribution and extraction models in the Indonesian Language. The experiments are conducted using five deep-learning model architectures with two different corpus sizes to investigate the impact of corpus size on each model’s performance. The experiments show that the best model for the RNN-based architecture is PFSA-ID-BLWCA which achieves 81.34 % F1 score, and the best model for the transformer-based is PFSA-ID-TWCA which obtains 81.01 % F1 score. This research also discovers that the size of the corpus influences the model performances. Furthermore, the study lays a foundation to overcome the attribution extraction in another language, especially low-resource languages, with some necessary adjustments.

PFSA-ID: An Annotated Indonesian Corpus and Baseline Model of Public Figures Statements Attributions

2 minute read

Published:

By far, the corpus for the quotation extraction and quotation attribution tasks in Indonesian is still limited in quantity and depth. This study aims to develop an Indonesian corpus of public figure statements attributions and a baseline model for attribution extraction, so it will contribute to fostering research in information extraction for the Indonesian language.

Understanding quotation extraction and attribution: towards automatic extraction of public figure’s statements for journalism in Indonesia

3 minute read

Published:

Extracting information from unstructured data becomes a challenging task for computational linguistics. Public figure’s statement attributed by journalists in a story is one type of information that can be processed into structured data. Therefore, having the knowledge base about this data will be very beneficial for further use, such as for opinion mining, claim detection and fact-checking. This study aims to understand statement extraction tasks and the models that have already been applied to formulate a framework for further study.

Research about Named Entity Recognition Published in ArXiv

2 minute read

Published:

Named Entity Recognition (NER) is a task in Information Extraction consisting in identifying and classifying just some types of information elements, called Named Entities (NE). I have tried to collect and curate some publications form Arxiv that related to NER, and the results were listed here. Please enjoy it!