An Improved of Stemming Algorithm for Mining Indonesian Text with Slang on Social Media

Maylawati, Dian Sa’adillah; Zulfikar, Wildan Budiawan; Slamet, Cepy; Ramdhani, Muhammad Ali; Gerhana, Yana Aditia

doi:10.1109/citsm.2018.8674054

Cited by 27 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The pre-processing text data begins with preparing data collection from the real data into clean data text after data cleaning, stopwords removal, and stemming process. For stopwords, it used the modified collection of Indonesian stopwords and Porter Stemming so that the structure and grammar are suitable with the Indonesian language [26,43]. Table 1 shows the example of the original Indonesian News data that becomes the data after text pre-processing.…”

Section: Results Of Text Pre-processingmentioning

confidence: 99%

Indonesian news classification using convolutional neural network

Ramdhani

Maylawati

Mantoro

2020

IJEECS

View full text Add to dashboard Cite

<span>Every language has unique characteristics, structures, and grammar. Thus, different styles will have different processes and result in processed in Natural Language Processing (NLP) research area. In the current NLP research area, Data Mining (DM) or Machine Learning (ML) technique is popular, especially for Deep Learning (DL) method. This research aims to classify text data in the Indonesian language using Convolutional Neural Network (CNN) as one of the DL algorithms. The CNN algorithm used modified following the Indonesian language characteristics. Thereby, in the text pre-processing phase, stopword removal and stemming are particularly suitable for the Indonesian language. The experiment conducted using 472 Indonesian News text data from various sources with four categories: ‘hiburan’ (entertainment), ‘olahraga’ (sport), ‘tajuk utama’ (headline news), and ‘teknologi’ (technology). Based on the experiment and evaluation using 377 training data and 95 testing data, producing five models with ten epoch for each model, CNN has the best percentage of accuracy around 90,74% and loss value around 29,05% for 300 hidden layers in classifying the Indonesian News data.</span>

show abstract

Section: Results Of Text Pre-processingmentioning

confidence: 99%

Indonesian news classification using convolutional neural network

Ramdhani

Maylawati

Mantoro

2020

IJEECS

View full text Add to dashboard Cite

show abstract

“…Even tough, in several research in text mining, the stemming process does not give a big effect in accuracy [45]. Stemming process is depend on the language, from many Indonesian stemming algorithm [46][47][48][49], this research use an improved Porter algorthm that modified based on Indonesian language [50]. The example result of text pre-processing is available in Table 2 which is pre-processing result from the text hadits example from Table 1 that provided in Indonesian Language.…”

Section: Text Pre-processingmentioning

confidence: 99%

Weighted inverse document frequency and vector space model for hadith search engine

Pratama

Darmalaksana

Maylawati

et al. 2020

IJEECS

Self Cite

View full text Add to dashboard Cite

Hadith is the second source of Islamic law after Qur’an which make many types and references of hadith need to be studied. However, there are not many Muslims know about it and many even have difficulties in studying hadiths. This study aims to build a hadith search engine from reliable source by utilizing Information Retrieval techniques. The structured representation of the text that used is Bag of Word (1-term) with the Weighted Inverse Document Frequency (WIDF) method to calculate the frequency of occurrence of each term before being converted in vector form with the Vector Space Model (VSM). Based on the experiment results using 380 texts of hadith, the recall value of WIDF and VSM is 96%, while precision value is just around 35.46%. This is because the structured representation for text that used is bag of words (1-gram) that can not maintain the meaning of text well).

show abstract

“…Oleh karena itu, penelitian ini bertujuan untuk menangani overstemming dengan melakukan perubahan (modifikasi) pada proses stemming. Proses perubahan (modifikasi) stemming dilakukan dengan menggabungkan algoritma look-up table yang berisi tabel aturan kata dan algoritma stemming Porter yang sudah dikenal [8], [9]. Tabel aturan kata tersebut dimasukkan ke dalam database sehingga dapat memudahkan proses update jenis kata yang mengalami overstemming.…”

Section: P-issn: 2621-8070 E-issn:2686-3219unclassified

Analisa Modifikasi Algoritma Stemming Untuk Kasus Overstemming

Hersianie

2020

teknokom

View full text Add to dashboard Cite

Overstemming merupakan pemenggalan kata ke bentuk asal (root word) yang berlebihan. Hal ini menyebabkan kata tersebut bermakna sangat berbeda dengan kata asal. Namun, stem yang dihasilkan sama bentuknya. Untuk mengatasi permasalahan tersebut, penelitian sebelumnya telah menerapkan algoritma stemming dengan tabel aturan kata. Namun kekurangan dari tabel aturan kata ini adalah kesulitan dalam menambahkan jenis kata yang mengalami overstemming. Oleh karena itu, penelitian ini bertujuan untuk memodifikasi algoritma overstemming tersebut. Penelitian ini akan menggabungkan algoritma stemming (hybrid stemming) yaitu algoritma look-up table, tabel aturan kata dan algoritma stemming Porter yang biasa digunakan. Dataset yang digunakan dalam pengujian adalah atribut judul pada dokumen publikasi ilmiah. Hasil pengujian menunjukkan bahwa modifikasi algoritma stemming menghasilkan recall sebesar 89, 9%.Saran untuk penelitian selanjutnya adalah pengujian dapat dilakukan menggunakan atribut lainnnya pada dokumen publikasi.

show abstract

An Improved of Stemming Algorithm for Mining Indonesian Text with Slang on Social Media

Cited by 27 publications

References 13 publications

Indonesian news classification using convolutional neural network

Indonesian news classification using convolutional neural network

Weighted inverse document frequency and vector space model for hadith search engine

Analisa Modifikasi Algoritma Stemming Untuk Kasus Overstemming

Contact Info

Product

Resources

About