Claim Missing Document
Check
Articles

Found 8 Documents
Search

Sentence Extraction Based on Sentence Distribution and Part of Speech Tagging for Multi-Document Summarization Agus Zainal Arifin; Moch Zawaruddin Abdullah; Ahmad Wahyu Rosyadi; Desepta Isna Ulumi; Aminul Wahib; Rizka Wakhidatus Sholikah
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 16, No 2: April 2018
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v16i2.8431

Abstract

Automatic multi-document summarization needs to find representative sentences not only by sentence distribution to select the most important sentence but also by how informative a term is in a sentence. Sentence distribution is suitable for obtaining important sentences by determining frequent and well-spread words in the corpus but ignores the grammatical information that indicates instructive content. The presence or absence of informative content in a sentence can be indicated by grammatical information which is carried by part of speech (POS) labels. In this paper, we propose a new sentence weighting method by incorporating sentence distribution and POS tagging for multi-document summarization. Similarity-based Histogram Clustering (SHC) is used to cluster sentences in the data set. Cluster ordering is based on cluster importance to determine the important clusters. Sentence extraction based on sentence distribution and POS tagging is introduced to extract the representative sentences from the ordered clusters. The results of the experiment on the Document Understanding Conferences (DUC) 2004 are compared with those of the Sentence Distribution Method. Our proposed method achieved better results with an increasing rate of 5.41% on ROUGE-1 and 0.62% on ROUGE-2.
Weighted k Nearest Neighbor Using Grey Relational Analysis To Solve Missing Value Desepta Isna Ulumi; Daniel Siahaan
IPTEK The Journal for Technology and Science Vol 29, No 3 (2018)
Publisher : IPTEK, LPPM, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (497.699 KB) | DOI: 10.12962/j20882033.v29i3.5011

Abstract

Software defect prediction model is an important role in detecting the most vulnerable component error software. Some research have been worked to improve the accuracy of the prediction defects of the software in order to manage human, costs and time. But previous research used specific dataset for software defect prediction model. However, there is no a generic dataset handling for software defect prediction model yet. This research proposed improvements to the results of the software defect prediction on the merged dataset, which is called generic dataset, with a number of different features. In order to balance the number of features, each dataset should be filled with a missing value. To fill the missing values, Weighted k Nearest Neighbor (WkNN) method was used. Then, after missing values were filled, Naïve Bayes was used to classify the selected features. This research needed to obtain a set of features which was relevant, then performed a feature selection method. The results showed that by using seven NASA public MDP datasets, Naïve Bayes with Information Gain (IG) or Symmetric Uncertainty (SU) feature selection presented the best balance value.Software defect, NASA public MDP, weighted KNN,Naive Bayes
Audit Tenoss Menggunakan Cobit 5 Pada Domain Deliver, Service And Support (dss) Desepta Isna Ulumi; Eko Darwiyanto; Yanuar Firdaus
eProceedings of Engineering Vol 2, No 2 (2015): Agustus, 2015
Publisher : eProceedings of Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Abstrak TeNOSS (Telkom National Operation Support System) merupakan objek di PT Telekomunikasi Indonesia Tbk yang berperan sebagai monitoring terhadap peningkatan pelayanan kepada pelanggan. Semua data pelanggan masuk dalam TeNOSS baik alamat, nomor telepon dan menggunakan produk Telkom apa saja pelanggan tersebut. Sehingga di dalam TeNOSS terdapat banyak data yang diolah. Pengelolaan TeNOSS memerlukan audit untuk mengevaluasi, mengukur kualitas dan memberi rekomendasi agar sesuai dengan tujuan organisasi. Dalam penelitian ini menggunakan framework COBIT 5 pada domain Deliver, Service and Support (DSS). Berdasarkan hasil mapping strategi bisnis yang didapatkan dari rencana strategi bisnis PT Telkom dipetakan ke dalamm Enterprise Goal dan IT Related Goal COBIT 5, didapatkan 3 proses untuk dinilai yaitu DSS02, DSS05, dan DSS06. Hasil penilaian menunjukkan DSS02 dan DSS06 berada pada level 3 yaitu established di mana level 2 kini diimplementasikan menggunakan proses didefinisikan yang mampu mencapai hasil prosesnya. Sedangkan DSS02 berada pada level 2 yaitu managed di mana level 1 kini diimplementasikan dalam model yang terkelola (direncanakan, dimonitor dan disesuaikan) dengan kinerja produk tepat didirikan, dikendalikan, dan dipelihara. Diharapkan dapat mencapai target optimalnya pada level 4 untuk DSS02 dan DSS06, sedangkan level 3 untuk DSS05. Kata Kunci : Audit, TeNOSS, COBIT 5, domain DSS.
Incorporating User Experience Evaluation into Application Design for Optimal Usability Helen Sastypratiwi; Yulianti Yulianti; Hafiz Muhardi; Desepta Isna Ulumi
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol 22 No 3 (2023)
Publisher : LPPM Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v22i3.2793

Abstract

Forest and land fires have become a national issue every year, especially in West Kalimantan. From 2015 to 2020, around 331,268.35 hectares of forest and land were burned in West Kalimantan. As a result of forest and land fires, the haze disrupts public health, the economy, and river, land, sea, and air transportation. As anticipation and prevention, the community and government monitor forest and land fires using the Forest Fire Monitoring System Application. The purpose of this study was to the User Experience (UX) evaluation for design improvement in the Forest Fire Monitoring System Application (SIPONGI) inWest Kalimantan. The method used was User Centered Design (UCD) and Website Usability Evaluation Tool (WEBUSE) to provide new design solutions in the form of a website prototype. The research methodology included a literature study of the SIPONGI application. The study used a sample of 25 respondents with different work backgrounds to represent the population using the SIPONGI application. The results of this study showed that usability points per attribute and category are superior after making UI/UX improvements using the UCD process in prototype form. In conclusion, using the UCD method is better if it is accompanied by the WEBUSE method in improving the design of an application.
Meningkatkan efektivitas pembelajaran di era digital melalui pelatihan pengembangan video pembelajaran interaktif Desepta Isna Ulumi; Herry Sujaini; Anggi Perwitasari; Haried Novriando
ABSYARA: Jurnal Pengabdian Pada Masayarakat Vol 4 No 2 (2023): ABSYARA: Jurnal Pengabdian Pada Masyarakat
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/ab.v4i2.24251

Abstract

Effective teaching in the digital era poses a major challenge in education, especially in elementary schools. This study highlights the importance of interactive learning media in enhancing teaching quality. Utilizing methods of presentation, discussion, and mentoring, this training targeted 50 elementary school teachers at SDN 39 and SDN 08 Sungai Kakap. The main focus was on creating educational videos using Microsoft PowerPoint, a software commonly used by teachers. The training content included the definition of educational videos, steps in video creation, tips for making engaging videos, and using PowerPoint for educational purposes. Pre-tests and post-tests were conducted to measure participants' understanding before and after the training. Results showed a significant improvement in understanding and skills in creating educational videos, with average pre-test scores rising from 54 to 93 in post-tests. Participants realized that PowerPoint is not only for presentations but also an effective tool for creating engaging and efficient educational videos. This research affirms that technology-based interactive learning, such as PowerPoint educational videos, enhances teachers' enthusiasm and student engagement, and supports teaching effectiveness in elementary schools. The main conclusion is that educational technology training like this is crucial for enhancing teachers' creativity and the quality of learning in the digital era.
Web Service pada Sistem Curriculum Vitae (CV) Dosen Terintegrasi Berbasis Arsitektur REST API Ulumi, Desepta Isna; Perwitasari, Anggi
JUSTIN (Jurnal Sistem dan Teknologi Informasi) Vol 12, No 2 (2024)
Publisher : Jurusan Informatika Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/justin.v12i2.78344

Abstract

Software called web services serves as a connector that allows various systems to communicate with each other without being affected by platform differences and without connecting directly to a database. Web services allow existing services on the old system to communicate with the new system without changing either. In this research, we will explain the development of a web service that can integrate several websites in the Untan Information System (Tanjungpura University), namely SIAKAD (Digital Media for Academic Guidance, Monitoring and Assessment Services), SPOTA (Final Project Outline Support System) and SIMLPPM (System Management Information for Research and Community Service Institutions) so that the data contained in the three information systems can match each other in real time. In addition, this research uses REST API (Representational State Transfer Application Programming Interface) technology for data exchange. System testing uses black box testing which tests twelve menu features and seven submenus showing that the features can run well as well as the User Acceptance Test (UAT) which shows results of 89.89%. Test results show that the system is well received by users. It is hoped that with this system lecturers will automatically have a CV that is updated every year, according to data that has been input into other systems owned by Untan, so that CV documents can be produced for research needs, community service and so on. fast, efficient and error free. input data.
An Interactive Mobile Application for Gardening Education and Community Empowerment Developed Using the Waterfall Method Ulumi, Desepta Isna; Perwitasi, Anggi; Azalia, Clara Oxana; Hadiasmah, Anaqah Aisyah; Montass, Requestha Amorine
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.468

Abstract

Indonesia is currently facing a food crisis exacerbated by climate change, which disrupts agricultural patterns and causes crop failures. These disruptions lead to increased food prices and reduced purchasing power, particularly affecting the lower-income population. One sustainable solution is home gardening, which can enhance food availability and reduce household expenses. However, not everyone has the knowledge or resources to start gardening. To address this gap, the PANENKU application was developed as a mobile-based platform aimed at educating users on how to grow essential food crops such as chilies, shallots, and ginger. PANENKU integrates interactive learning through simulation games that guide users step-by-step, from planting to harvesting. The application leverages the Waterfall development model for systematic design and includes features such as AR (Augmented Reality) experiences, informative articles, and a community forum. These elements foster engagement, support peer-to-peer learning, and enhance users gardening knowledge. By incorporating educational gameplay and expert interaction, PANENKU not only supports individual self-sufficiency but also promotes environmental sustainability and strengthens local economies. System testing using black box testing which tests four features shows that the features can run well and the System Usability Scale (SUS) shows a result of 86%. The results of this test show that the app is particularly beneficial for housewives and beginner gardeners, offering an innovative and accessible approach to addressing food security challenges in Indonesia. Ultimately, PANENKU aspires to be a positive, inclusive platform for agricultural education and community empowerment.
Perbandingan Algoritma Support Vector Machine (SVM) dan Naive Bayes pada Analisis Sentimen Bahasa Jawa dan Sunda Putri, Galuh Kusuma; Sujaini, Herry; Ulumi, Desepta Isna
JUSTIN (Jurnal Sistem dan Teknologi Informasi) Vol 13, No 2 (2025)
Publisher : Jurusan Informatika Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/justin.v13i2.88285

Abstract

Perbedaan struktur kalimat, pilihan kata, dan tingkatkesopanan dalam Bahasa Jawa dan Sunda dibandingkan dengan Bahasa Indonesia membuat analisis sentimenmenjadi lebih kompleks. Karakteristik unik kedua bahasaini sering kali sulit dipahami, terutama bagi bukan penuturaslinya, sehingga metode pemrosesan teks yang umumdigunakan untuk Bahasa Indonesia tidak selalu efektif. Oleh karena itu, diperlukan pendekatan yang dapatmengklasifikasikan sentimen teks berbahasa daerah ini, apakah bersifat positif, negatif, atau netral, gunameningkatkan pemahaman terhadap opini masyarakat sertamemperluas aksesibilitas informasi. Mengingat tantangantersebut, penelitian ini berfokus pada eksplorasi metodeklasifikasi yang dapat secara efektif menanganikarakteristik unik dari Bahasa Jawa dan Sunda dalamanalisis sentimen. Untuk itu, penelitian ini bertujuanmelakukan perbandingan antara algoritma Support Vector Machine (SVM) dan Naive Bayes guna menentukanpendekatan yang paling sesuai dalam mengklasifikasikansentimen teks pada kedua bahasa ini. SVM mencari garis pemisah terbaik untuk mengklasifikasikan data, sedangkanNaive Bayes menggunakan perhitungan probabilitasberdasarkan pola kata yang muncul. Dalam penelitian iniekstraksi fitur dilakukan menggunakan TF-IDF dan seleksifitur menggunakan Chi-Square. Data yang digunakan dariIndonesian NLP data catalogue yang terdata mulai daritahun 2020-2023. Hasil penelitian menunjukkan bahwametode klasifikasi Support Vector Machine (SVM) lebihbaik dari pada Naive Bayes di kedua bahasa. SVM mendapatkan akurasi pada Bahasa Jawa sebesar 76% dan Bahasa Sunda sebesar 80% sedangkan Naive Bayes pada Bahasa Jawa sebesar 73% dan Bahasa Sunda sebesar 77%. SVM menjadi metode terbaik dalam penelitian ini karenamenunjukkan performa yang lebih baik pada kedua bahasadibandingkan Naive Bayes.