Afrida Helen, Afrida
Department of Informatics, School of Electrical Engineering and Informatics (STEI) Bandung Institute of Technology, Jalan Ganesha 10, Bandung, 40132

Published : 6 Documents
Articles

Found 6 Documents
Search

Rhetorical Sentences Classification Based on Section Class and Title of Paper for Experimental Technical Papers Helen, Afrida; Purwarianti, Ayu; Widyantoro, Dwi H.
Journal of ICT Research and Applications Vol 9, No 3 (2015)
Publisher : ITB Journal Publisher, LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (246.844 KB) | DOI: 10.5614/itbj.ict.res.appl.2015.9.3.5

Abstract

Rhetorical sentence classification is an interesting approach for making extractive summaries but this technique still needs to be developed because the performance of automatic rhetorical sentence classification is still poor. Rhetorical sentences are sentences that contain rhetorical words or phrases. Rhetorical sentences not only appear in the contents of a paper but also in the title. In this study, features related to section class and title class that have been proposed in a previous research were further developed. Our method uses different techniques to reach automatic section class extraction for which we introduce new, format-based features. Furthermore, we propose automatic rhetoric phrase extraction from the title. The corpus we used was a collection of technical-experimental scientific papers. Our method uses the Support Vector Machine (SVM) algorithm and the Naïve Bayesian algorithm for classification. The four categories used were: Problem, Method, Data, and Result. It was hypothesized that these features would be able to improve classification accuracy compared to previous methods. The F-measure for these categories reached up to 14%. 
Automatic Abstractive Summarization Task for New Article Helen, afrida
EMITTER International Journal of Engineering Technology Vol 6, No 1 (2018)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (36.352 KB) | DOI: 10.24003/emitter.v6i1.212

Abstract

Understanding the contents of numerous documents requires strenuous effort. While manually reading the summary or abstract is one way, automatic summarization offers more efficient way in doing so. The current research in automatic summarization focuses on the statistical method and the Natural Processing Language (NLP) method.Statistical method produce Extractive summary that the summaries consist of independent sentences considered important content of document. Unfortunately, the coherence of the summary is poor. Besides that, the Natural Processing Language expected can produces summary where sentences in summary should not be taken from sentences in the document, but come from the person making the summary. So, the summaries closed to human-summary, coherent and well structured.This study discusses the tasks of generating summary. The conclusion is we can find that there are still opportunities to develop better outcomes that are better coherence and better accuracy.
Rule-based Sentiment Degree Measurement of Opinion Mining of Community Participatory in the Government of Surabaya Putra, Berlian Juliartha Martin; Helen, Afrida; Barakbah, Ali Ridho
EMITTER International Journal of Engineering Technology Vol 6, No 2 (2018)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (423.153 KB) | DOI: 10.24003/emitter.v6i2.275

Abstract

Diskominfo Surabaya, as a government agency, received much community participatory for improvement of governmental services, with increasing number of 698, 2717, 4176 and 4298 participatory data respectively in 2011, 2012, 2013 and 2014. It is challenging for Diskominfo Surabaya to set a target by giving the response back within 24 hours. Due to task complexity to address the degree of participatory and to categorize the group of participatory, they faced difficulty to fulfill the target. In this research, we present a new system for measuring the sentiment degree of community participatory. We provide 5 functions in our system, which are: (1) Data Collection, (2) Data Preprocessing, (3) Text Mining, (4) Sentiment Analysis and (5) Validation. We propose our rule-based technique for the sentiment analysis of opinion mining with detection of 8 important parts, which are (1) Verb, (2) Adjective, (3) Preposition, (4) Noun, (5) Adverb, (6) Symbol, (7) Phrase, and (8) Complimentary. For applicability of our proposed system, we made a series of experiment with 410 data of community participatory in Twitter for Diskominfo Surabaya and compared with other sentiment classification algorithms which are SVM and Naive Bayes Classifier. Our system performed 77.32% rate of accuracy and outperformed to other comparing algorithms.
Semantic Information Retrival for Scientific Experimental Papers with Knowlege based Feature Extraction Mubatada'i, Nur Rosyid; Barakbah, Ali Ridho; Helen, Afrida
INOVTEK Polbeng - Seri Informatika Vol 4, No 1 (2019)
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1205.402 KB) | DOI: 10.35314/isi.v4i1.885

Abstract

Seiring dengan perkembangan zaman, jumlah karya ilmiah semakin meningkat. Permintaan pencarian informasi dalam makalah ilmiah juga meningkat. Pada  makalah ilmiah eksperimental, peneliti mengalami kesulitan dalam mencari informasi pada karya ilmiah eksperimental karena mesin pencari informasi memiliki keterbatasan dalam proses pencarian berdasarkan ekstraksi fitur berbasis text-mining dari seluruh teks, sedangkan jenis makalah ilmiah eksperimental memiliki konten spesifik, yang memiliki perlakuan berbeda dalam ekstraksi fitur. Dalam makalah ini, kami mengusulkan sistem baru untuk pengambilan informasi pada makalah ilmiah eksperimental. Sistem ini terdiri dari 4 fungsi utama: (1) Ekstraksi fitur berbasis konten spesifik, (2) Model klasifikasi, (3) Pemilihan subruang berbasis konteks, dan (4) Pengukuran kesamaan yang bergantung pada konteks. Dalam ekstraksi fitur, sistem kami mengekstraksi kategori fitur dalam makalah ilmiah eksperimental dengan fitur berbasis konten tertentu, yaitu data, masalah, metode, dan hasil. Untuk model klasifikasi, kami menggunakan beberapa algoritma klasifikasi untuk mengklasifikasikan fitur konten tertentu dari paper queri ke agregasi dokumen pembelajaran. Dalam Pemilihan Subruang Berbasis Konteks, sistem melakukan pengurangan dimensi dengan pemilihan subruang berbasis konteks yang dipilih oleh pengguna. Untuk mendapatkan hasil pencarian akhir, kami mengukur kesamaan konteks dengan membangun metrik dataset berdasar konteks ke paper. Untuk melakukan penerapan sistem yang kami usulkan, kami menguji 77 makalah dalam dataset dengan model validasi Leave-One-Out dengan beberapa algoritma klasifikasi (Nearest Neighbor, Naive Bayes, Support Vector Machine, dan Decision Tree) dan rata-rata melakukan presisi 66,65% tingkat dan akurasi tingkat presisi 76,18%. Kami juga melakukan percobaan pada pengukuran kesamaan dengan memberikan queri paper dan konten yang diinginkan (data, hasil, metode, dan masalah) sebagai konteks yang diberikan oleh pengguna. Dalam percobaan pengukuran kesamaan, sistem yang kami usulkan memiliki tingkat akurasi 79,17%.
Automatic Abstractive Summarization Task for New Article Helen, Afrida
EMITTER International Journal of Engineering Technology Vol 6 No 1 (2018)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (36.352 KB) | DOI: 10.24003/emitter.v6i1.212

Abstract

Understanding the contents of numerous documents requires strenuous effort. While manually reading the summary or abstract is one way, automatic summarization offers more efficient way in doing so. The current research in automatic summarization focuses on the statistical method and the Natural Processing Language (NLP) method. Statistical method produce Extractive summary that the summaries consist of independent sentences considered important content of document. Unfortunately, the coherence of the summary is poor. Besides that, the Natural Processing Language expected can produces summary where sentences in summary should not be taken from sentences in the document, but come from the person making the summary. So, the summaries closed to human-summary, coherent and well structured. This study discusses the tasks of generating summary. The conclusion is we can find that there are still opportunities to develop better outcomes that are better coherence and better accuracy.
Rule-based Sentiment Degree Measurement of Opinion Mining of Community Participatory in the Government of Surabaya Putra, Berlian Juliartha Martin; Helen, Afrida; Barakbah, Ali Ridho
EMITTER International Journal of Engineering Technology Vol 6 No 2 (2018)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (423.153 KB) | DOI: 10.24003/emitter.v6i2.275

Abstract

Diskominfo Surabaya, as a government agency, received much community participatory for improvement of governmental services, with increasing number of 698, 2717, 4176 and 4298 participatory data respectively in 2011, 2012, 2013 and 2014. It is challenging for Diskominfo Surabaya to set a target by giving the response back within 24 hours. Due to task complexity to address the degree of participatory and to categorize the group of participatory, they faced difficulty to fulfill the target. In this research, we present a new system for measuring the sentiment degree of community participatory. We provide 5 functions in our system, which are: (1) Data Collection, (2) Data Preprocessing, (3) Text Mining, (4) Sentiment Analysis and (5) Validation. We propose our rule-based technique for the sentiment analysis of opinion mining with detection of 8 important parts, which are (1) Verb, (2) Adjective, (3) Preposition, (4) Noun, (5) Adverb, (6) Symbol, (7) Phrase, and (8) Complimentary. For applicability of our proposed system, we made a series of experiment with 410 data of community participatory in Twitter for Diskominfo Surabaya and compared with other sentiment classification algorithms which are SVM and Naive Bayes Classifier. Our system performed 77.32% rate of accuracy and outperformed to other comparing algorithms.