Article Per Year (5 Year)
p-Index From 2020 - 2025
1.497
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering JOIV : International Journal on Informatics Visualization Jiko (Jurnal Informatika dan komputer) JISKa (Jurnal Informatika Sunan Kalijaga) Khazanah Pendidikan Islam International Journal of Islamic Khazanah Journal of Applied Data Sciences Jurnal Algoritma Jurnal Informatika Polinema (JIP)
Maylawati, Dian Sa'adillah
Unknown Affiliation
Religion Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Library & Information Science Mathematics Public Health Social Sciences Other

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

 1 
Deep sequential pattern mining for readability enhancement of Indonesian summarization Maylawati, Dian Sa'adillah; Kumar, Yogan Jaya; Kasmin, Fauziah; Ramdhani, Muhammad Ali
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 1: February 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i1.pp782-795

Abstract

In text summarization research, readability is a great issue that must be addressed. Our hypothesis is readability can be accomplished by using text representations that keep the meaning of text documents intact. Therefore, this study aims to combine sequential pattern mining (SPM) in producing a sequence of a word as text representation with unsupervised deep learning to produce an Indonesian text summary called DeepSPM. This research uses PrefixSpan as an SPM algorithm and deep belief network (DBN) as an unsupervised deep learning method. This research uses 18,774 Indonesian news text from IndoSum. The readability aspect is evaluated by recall-oriented understudy for gisting evaluation (ROUGE) as a co-selection-based analysis; Dwiyanto Djoko Pranowo metrics, Gunning fog index (GFI), and Flesch-Kincaid grade level (FKGL) as content-based analysis; and human readability evaluation with two experts. The experiment result shows that DeepSPM yields better than DBN, with the F-measure value of ROUGE-1 enhanced to 0.462, ROUGE-2 is 0.37, and ROUGE-L is 0.41. The significance of ROUGE results also be tested using T-Test. The content-based analysis and human readability evaluation findings are conformable with the findings of co-selection-based analysis that generated summaries are only partially readable or have a medium level of readability aspect.
Bidirectional and Auto-Regressive Transformer (BART) for Indonesian Abstractive Text Summarization Hartawan, Gaduh; Maylawati, Dian Sa'adillah; Uriawan, Wisnu
Jurnal Informatika Polinema Vol. 10 No. 4 (2024): Vol. 10 No. 4 (2024)
Publisher : UPT P2M State Polytechnic of Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jip.v10i4.5242

Abstract

Automatic summarization technology is developing rapidly to reduce reading time and obtain relevant information in Natural Language Processing technology research. There are two main approaches to text summarization: abstractive and extractive. The challenge of abstractive summarization results is higher than abstractive because abstractive summarization produces new and more natural words. Therefore, this research aims to produce abstractive summaries from Indonesian language texts with good readability. This research uses the Bidirectional and Auto-Regressive Transformer (BART) model, an innovative Transformers model combining two leading Transformer architectures, namely the BERT encoder and GPT decoder. The dataset used in this research is Liputan6, with model performance evaluation using ROUGE evaluation. The research results show that BART can produce good abstractive summaries with ROUGE-1, ROUGE-2, and ROUGE-L values of 37.19, 14.03, and 33.85, respectively.
Exploring Classification Algorithms for Detecting Learning Loss in Islamic Religious Education: A Comparative Study Sapdi, Rohmat Mulyana; Maylawati, Dian Sa'adillah; Ramdania, Diena Rauda; Budiman, Ichsan; Al-Amin, Muhammad Insan; Fuadi, Mi'raj
JOIV : International Journal on Informatics Visualization Vol 8, No 2 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.2.1823

Abstract

This study investigates the detection of learning loss in Islamic religious education subjects in Indonesia. Focusing on the effectiveness of multiple classification algorithms, the research assesses learning loss across literacy, numeracy, writing, and science domains. While education traditionally involves knowledge transmission, it also seeks to instill values. Given Indonesia's predominantly Islamic demographic, Islamic Religious Education (IRE) is pivotal in disseminating moral and cultural values, encompassing teachings from the Koran, Hadith, Aqedah, morality, Fiqh, and Islamic history. The study's central aim is to discern learning loss in IRE in Islamic schools, utilizing the Gradient Boosting Classifier as its primary analytical tool. Various classification algorithms, including the Cat Boost Classifier, Light Gradient Boosting Machine, Extreme Gradient Boosting, and others, were tested. The study engaged a sample of 38,326 Islamic Elementary school students, 29,350 Islamic Junior High school students, and 13,474 Islamic High school students across Indonesia. The findings revealed that the Light Gradient Boosting Machine was the most effective model for Islamic Elementary and High school data, while the Cat Boost Classifier excelled for Islamic Junior High school data. These results highlight the extent of learning loss in IRE and offer invaluable perspectives for education stakeholders. Future studies are encouraged to further explore the root causes of this learning loss and devise specific interventions to tackle these issues effectively.
Chatbot Edukasi Pra-Nikah berbasis Telegram Menggunakan Bidirectional Encoder Representations From Transformers (BERT) Fatonah, Fany Risti; Maylawati, Dian Sa'adillah; Nurlatifah, Eva
Jurnal Algoritma Vol 21 No 2 (2024): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.21-2.1657

Abstract

Tingginya angka perceraian dan penurunan minat untuk menikah di Indonesia memunculkan kebutuhan akan pendekatan baru dalam edukasi pranikah. Dengan memanfaatkan teknologi Natural Language Processing, penelitian ini bertujuan untuk mengembangkan mesih chatbot menjadi solusi dalam edukasi pre-nikah yang dengan memberikan informasi efektif dan efisien kepada pasangan calon pengantin secara realtime. Penelitian ini menggunakan model Bidirectional Encoder Representations from Transformers (BERT) dengan chatbot berupa konteks dari website Kementerian Agama dan buku edukasi pernikahan. Model ini diimplementasikan ke dalam chatbot melalui platform Telegram dan pengujiannya menggunakan pengujian Non-Respon-Rate dan metriks BERTScore. Hasil pengujian Non-Respon-Rate menunjukkan akurasi chatbot edukasi pranikah berbasis BERT sebesar 76,92% dengan akurasi tertinggi 92%. Sedangkan pengujian menggunakan BERTScore menunjukkan bahwa chatbot tersebut mencapai nilai precision 86%, recall 83%, dan F1-score 84%.
Polarization of Religious Issues in Indonesia’s Social Media Society and Its Impact on Social Conflict Faizin, Barzan; Fitri, Susanti Ainul; AS, Enjang; Maylawati, Dian Sa'adillah; Rizqullah, Naufal; Ramdhani, Muhammad Ali
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.447

Abstract

In this new era, people use social media to share information and discuss political, social, and religious issues, leading to pros and cons arguments. In Twitter’s hashtags and tweets, religious issues frequently trigger a hot conversation that causes disputes among citizens and even street movements. This study is intended to reveal the religious issues that often trigger polarization among Twitter users and how they influence horizontal conflict in society as what happened during the election period in 2019. This research applied mixed methods with social media analytics to conceal religious issues in Indonesia's social media society. The data collection was done by crawling data from the Indonesian Twitter users’ tweets regarding religious issues hashtags, which is a reference for further analysis. The research findings show that the top eight religious issues widely discussed based on 23,433 Twitter users’ tweets are the hashtags (#) salafi, wahabi, intoleransi (intolerance), taliban, anti-Pancasila, politisasi agama (politicization of religion), politik identitas (identity politics), and radikalisme (radicalism). In social conversation networks, these issues are related to each other and other issues such as political figures, the three presidential candidates, the general election, and the Republic of Indonesia presidential election in 2024. Concerning these issues, Twitter users believe that the issues, positive or negative, do not influence their religious and political stance. However, to a certain extent, they believe that religious issues impact social discourses regarding horizontal conflicts. 44% opinions prove this indicated that the debate over religious matters had little influence on their opinion of these topics, and 64.5% agreed that religious concerns can cause social strife. Finally, it is hoped that further studies will elaborate on how religious issues on Twitter and other social media directly impact social harmony in everyday life.
Enhancing Abstractive Multi-Document Summarization with Bert2Bert Model for Indonesian Language Muharam, Aldi Fahluzi; Gerhana, Yana Aditia; Maylawati, Dian Sa'adillah; Ramdhani, Muhammad Ali; Rahman, Titik Khawa Abdul
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 10 No. 1 (2025): January 2025
Publisher : UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/jiska.2025.10.1.110-121

Abstract

This study investigates the effectiveness of the proposed Bert2Bert and Bert2Bert+Xtreme models in improving abstract multi-document summarization for Indonesians. This research uses the transformer model to develop the proposed Bert2Bert and Bert2Bert+Xtreme models. This research utilizes the Liputan6 data set, which comprises news data along with summary references spanning 10 years from October 2000 to October 2010, and is commonly used in many automatic text summarization studies. The model evaluation results using ROUGE-1, ROUGE-2, ROUGE-L, and BERTScore indicate that the proposed model exhibits a slight improvement over previous research models, with Bert2Bert performing better than Bert2Bert+Xtreme. Despite the challenges posed by limited reference summaries for Indonesian documents, content-based analysis using readability metrics, including FKGL, GFI, and Dwiyanto Djoko Pranowo, revealed that the summaries produced by Bert2Bert and Bert2Bert+Xtreme are at a moderate readability level, meaning they are suitable for mature readers and align with the news portal’s target audience.
In-depth Sentiment Analysis of The Independent Campus Program in Islamic Higher Education using Abstractive Summarization Maylawati, Dian Sa'adillah; Saputra, Muhammad Indra Nurardy; Syahrifudin, Umar; Muharam, Aldi Fahluzi
Khazanah Pendidikan Islam Vol. 6 No. 3 (2024): Khazanah Pendidikan Islam
Publisher : UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/kpi.v6i3.44500

Abstract

The implementation of the Merdeka Belajar Kampus Merdeka (MBKM) policy in Islamic Higher Education (PTKI) represents a significant shift in Indonesia’s education system. This study evaluates the impact of MBKM on PTKI institutions using sentiment analysis and automatic text summarization. By analyzing 2,416 tweets (2020-2023) from PTKI academics, this study highlights perceptions, challenges, and policy implications. Results indicate that 82.76% of tweets expressed positive sentiment, emphasizing the benefits of MBKM in curriculum flexibility and industry collaboration. However, 17.24% of tweets highlighted challenges, including policy mismanagement, unclear implementation, and student stress. To enhance policy effectiveness, this study recommends stronger institutional support, clearer policy guidelines, and enhanced digital infrastructure to ensure MBKM benefits all PTKI students equitably.
AUTOMATIC ABSTRACTIVE SUMMARIZATION OF CURRICULUM VITAE USING S-BERT AND T5 Herdiyanto, Reza Fahlevi; Maylawati, Dian Sa'adillah; Lukman, Nur
JIKO (Jurnal Informatika dan Komputer) Vol 8, No 2 (2025)
Publisher : Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v8i2.10019

Abstract

The rapid advancement of technological disruption has catalyzed significant innovations in human resource management, particularly through the widespread adoption of automated applicant screening systems such as Applicant Tracking Systems (ATS). However, these systems often fail to identify potential candidates due to poorly formatted Curriculum Vitae (CV) or missing important keywords, resulting in many applicants being eliminated in the early stages of selection. This research aims to develop an automatic CV summarization system by utilizing Natural Language Processing (NLP) technology. This research uses a combination of Sentence-BERT (SBERT) algorithm for information extraction and Text-to-Text Transfer Transformer (T5) for text generation. The K-Fold Cross Validation method with k = 3 was used in the model performance evaluation, in accordance with the limited computing resources. Experimental results show that the SBERT model is able to extract important information with high accuracy (F1-score of 0.8866), while the T5 model is able to generate informative summaries with a ROUGE-1 score of 0.8680. The combination of SBERT in producing important information extraction from CV and T5 that produces an abstractive summary shows good results with ROUGE-1 scores of 0.5497, ROUGE-2 of 0.3537, and ROUGE-L of 0.4334. This system is able to produce CV summaries that make it easier for companies to select job applicants according to the criteria and increase the chances of applicants to pass the initial selection stage
Society's Perspectives on Contemporary Islamic Law in Indonesia through Social Media Analysis Technology: A Preliminary Study Maylawati, Dian Sa'adillah; Khosyi'ah, Siah; Kholiq, Achmad
International Journal of Islamic Khazanah Vol. 12 No. 1 (2022): IJIK
Publisher : UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/ijik.v12i1.15865

Abstract

The social, cultural, and technological developments of society are unavoidable. This has an impact on the development of Islamic Law, which keeps all Muslim activities in the right corridor. Contemporary Islamic law, known as Contemporary Islamic Law, has also developed to answer new societal problems. Various views on Contemporary Islamic Law in solving multiple issues certainly reap various responses from the community and scholars. These views are often conveyed through social media such as Youtube, Instagram, Facebook, and Twitter. Therefore, this article aims to discuss a preliminary study of text analysis techniques used to find out the views of the community and Ulama on Contemporary Islamic Law issues computationally and automatically. This initial study reviews the methods and techniques that will be used, namely the Indonesian National Work Competency Standards (SKKNI) methodology for data science. This study will also use a sentiment analysis approach, topic modeling, and pattern analysis to find out people's views on issues of Contemporary Islamic Law through social media. The algorithm used for sentiment analysis is the Multinomial Naïve Bayes Classifier (MNBC), for topic modeling is Latent Dirichlet Allocation (LDA), while for pattern analysis using the Prefix-projected Sequential Pattern Mining (PrefixSpan) algorithm. The model generated from sentiment analysis, topic modeling, and pattern analysis will be evaluated by measuring the confusion matrix, coherence value, and silhouette coefficient value. In addition, analysis and interpretation of the model results will be carried out in-depth qualitatively by involving the views and thoughts of Islamic Law experts.
Co-Authors Barzan Faizin Diena Rauda Ramdania Enjang AS, Enjang Fatonah, Fany Risti Fitri, Susanti Ainul Hartawan, Gaduh Herdiyanto, Reza Fahlevi Ichsan Budiman Kasmin, Fauziah Kholiq, Achmad Khosyi'ah, Siah Kumar, Yogan Jaya Mi’raj Fuadi Muhammad Ali Ramdhani Muhammad Insan Al-Amin Muharam, Aldi Fahluzi Nur Lukman Nurlatifah, Eva Rahman, Titik Khawa Abdul Rizqullah, Naufal Rohmat Mulyana Sapdi Saputra, Muhammad Indra Nurardy Syahrifudin, Umar Wisnu Uriawan, Wisnu Yana Aditia Gerhana, Yana Aditia