Garuda - Garba Rujukan Digital

Pengembangan Perangkat Microservices untuk Analisis Media Sosial sebagai Pendukung Pelacakan Penyebaran Tuberculosis Ronaldo Cristover Octavianus; Dzikri Robbi; Laras Ervintyana; Hapnes Toba
Jurnal Linguistik Komputasional Vol 5 No 1 (2022): Vol. 5, NO. 1
Publisher : Indonesia Association of Computational Linguistics (INACL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jlk.v5i1.70

Tuberculosis (TBC) adalah suatu penyakit menular yang disebabkan oleh kuman Mycobacterium Tuberculosis. Penyakit ini sangat berbahaya dan perlu ditangani segera jika ada yang terindikasi tertular, namun sangatlah sulit untuk melakukan pelacakan bagi mereka yang memiliki gejala karena pada awalnya sangat mirip dengan gejala batuk biasa. Riset yang dipaparkan dalam makalah ini bertujuan untuk mengumpulkan data dari media sosial yang terkait dengan penyakit TBC tersebut. Data media sosial, khususnya Twitter, akan diproses nilai sentimennya. Di samping itu, dikembangkan pula perangkat berbasis microservices guna melakukan ekstraksi data Twitter dan pengolahan dashboard pemberi informasi untuk wilayah yang disinyalir terdapat penderita TBC. Hasil penelitian menunjukkan bahwa tingkat akurasi sentimen perlu untuk ditingkatkan dengan model yang dilengkapi dengan kata-kata non-formal (slang) dan nuansa bahasa daerah. Namun demikian, infrastruktur pengolah data dengan berbasis pada microservices telah berhasil dikembangkan dengan baik, dan dapat digunakan pada aplikasi lain yang sejenis.

Pemanfaatan Epistemic Network Analysis sebagai Pendukung Analisis Sentimen dalam Collaborative Learning Roy Parsaoran; Jonathan Bernad; Tifani Astadini; Hapnes Toba; Maresha Caroline Wijanto; Mewati Ayub
Jurnal Linguistik Komputasional Vol 3 No 2 (2020): Vol. 3, No. 2
Publisher : Indonesia Association of Computational Linguistics (INACL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jlk.v3i2.36

A lot of blended learning methods have been applied to modern learning system. One of the most used learning methods is collaborative learning which combines and extends group discussion. The recorded data during a collaborative learning session could be useful to enhanced the interaction among the class members, including the lecturer. Using sentiment analysis, the discussion can be categorized whether the discussion goes well or not, it can also be seen which group members are most active and have a positive impact on the work assigned to the group. In this preliminary research, sentiment analysis approach will be combined with Epistemic Network Analysis (ENA) so that it can see a graphical depiction of each member's contribution in a group discussion. Our experimental results show that ENA displays better insights of the students activities than only using the sentiment analysis.

Pembuatan Aplikasi Bergerak Temu Ulang File Elektronik Berbahasa Indonesia dengan Memanfaatkan Java CLDC Andre Kurniawan; Hapnes Toba
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2009
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

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

Smart Download is a mobile application that dedicated to search electronic documents in Indonesian(Bahasa Indonesia) throguh the Web. This application use the Advanced URL Google (spyder) to retrieve thedocuments from the Internet, that further will be enchanced with Porter Stemmer and the combination ofTF/IDF and vector space algorithm. The documents that need to be downloaded can be breakdown in partialparts. The implementation of the application used J2ME CLDC. The application is evaluated in a classroomsituation, the result shows that search is improved after the enhancement process.Keywords: Smart Download, Spyder Google, Porter Stemmer, Vector Space Algorithm.

Pencarian Cerdas dengan Penggunaan Semantic Web Hapnes Toba
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2005
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

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

Pada artikel ini akan dibahas studi literatur mengenai teknologi pencarian data dengan menggunakankonsep pencarian cerdas. Perkembangan data di Internet ataupun sumber data elektronik tertentu sangat sulitdiikuti, setiap saat informasi pada suatu web site bisa berubah isinya, baik secara dinamik maupun statik. Salahsatu pendekatan yang dapat digunakan untuk untuk mengatasi masalah di atas adalah dengan melakukanpencarian data melalui mesin pencarian yang berbasiskan pada semantik dari sumber data yang didefinisikandalam ontology. Teknologi Internet yang digunakan dalam ontologi XML (eXtensible Markup Language) danRDF (Resource Description Framework). Keunggulan teknologi XML dan RDF adalah adanya jaminan untukinteroperabilitas antara sumber data yang tersebar di berbagai tempat dengan platform yang sama ataupunberbeda. Hasil dari penelitian literatur ini ditindaklanjuti dengan perancangan dan pembuatan suatu mesinpencarian cerdas yang ditujukan untuk pencarian data yang menunjang mahasiswa dalam pembuatan kerjapraktek atau tugas akhir. Pencarian tersebut akan dapat dilakukan di Internet ataupun suatu sumber datainternal tertentu, seperti misalnya database perpustakaan atau pengelolaan dokumen elektronik lainnya.Kata kunci: pencarian cerdas, ontologi, XML, RDF, web semantik, dokumen elektronik.

Pemanfaatan Teknologi Open Source pada Perpustakaan Sebagai Alternatif Penanggulangan Problema Kelestarian Dokumen Hapnes Toba
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2004
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

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

Using information technology applications in real life situation could give manyadvantages. One such advantages can be seen in library collection management. Building anapplication for the library management system could be done in low cost, efficient andflexible manner through the using of open sources technology. This article describes aninitiatiave and architectural design of an online electronic document management system atthe Library of Engineering Faculty Maranatha Christian University Bandung, through theusing of open-sources and e-content technology. The second part of this article gives a list ofproblems that should be anticipated to ensure that electronic documents can be useful notonly today but also in the future. Long-term preservation strategy through the using of XMLtechnology is a good possible solution for document preservation problem. This strategy hasbeen observed and evaluated in many research projects in the past 5 years.Keywords: digital library, open sources technology, document preservation, metadata, econtent.

Ekstraksi dan Analisis Produk di Marketplace Secara Otomatis dengan Memanfaatkan Teknologi Web Crawling Ivan Nathaniel Husada; Edward Hanafi Fernando; Hetthroh Sagala; Ariel Elbert Budiman; Hapnes Toba
Jurnal Teknik Informatika dan Sistem Informasi Vol 5 No 3 (2019): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v5i3.1977

Along with the advancement in technology, todays community begins to abandon conventional shopping methods where buyers must come to the seller's shop. Nowadays community mostly doing online shopping because the process is considered more convenience. Because of this, there are more and more online marketplace users. Much more data can be retrieved with the increasing number of online marketplace users. Because of the large amount of data the process for extracting the data so that it can be seen and utilized becomes possible. The purpose of this journal is to show data and extraction method from an online marketplace system so that the results can be visualized and users can analyze the data. The data extraction method that will be used is the web crawling method and web scraping where after the data is successfully extracted and cleaned it will be visualized with the power BI application. The experiments show that the method is useful to conduct analysis.

Pengaruh Metode Penyeimbangan Kelas Terhadap Tingkat Akurasi Analisis Sentimen pada Tweets Berbahasa Indonesia Ivan Nathaniel Husada; Hapnes Toba
Jurnal Teknik Informatika dan Sistem Informasi Vol 6 No 2 (2020): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v6i2.2743

Nowadays internet access is getting easier to get. Because of the ease of access to the internet, almost all internet users have social media. Social media is widely used by users to call out their opinions or even to make complaints about a matter and also discuss a topic with other social media users. From many existing social media, one that is popularly used for that activity is Twitter. Sentiment analysis on Twitter has become possible because of the activities of these Twitter users. In this research, the authors explore sentiment analysis with bag-of-words and Term Frequency Inverse Document Frequency (TF-IDF) features extraction based on tweets from Indonesian Twitter users. The data obtained is in imbalanced condition, so that it requires a method to overcome them. The method for overcoming imbalanced dataset uses a resampling approach which combines over and under sampling strategies. The results of sentiment analysis accuracies with Naïve Bayes and neural networks before and after input data resampling are also compared. Naïve Bayes methods that will be used are Multinomial Naïve Bayes and Complement Naïve Bayes, while the Neural Network architecture that will be used as a comparison are Recurrent Neural Networks, Long Short-Term Memory, Gated Recurrent Units, Convolutional Neural Networks, and a combination of Convolutional Neural Networks and Long Short-Term Memory. Our experiments show the following harmonic scores (F1) of the sentiment analysis models: the Multinomial Naïve Bayes F1 score is 55.48, Complement Naïve Bayes is 51.33, Recurrent Neural Network is 75.70, Long Short-Term Memory is 78.36, Gated Recurrent Unit is 77.96, Convolutional Neural Network is 76.12, and finally the combination of Convolutional Neural Networks and Long Short-Term Memory achieves 81.14.

Pemanfaatan Latent Semantic Indexing untuk Mengukur Potensi Kerjasama Jurnal Ilmiah Lintas Universitas Edward Hanafi Fernando; Hapnes Toba
Jurnal Teknik Informatika dan Sistem Informasi Vol 6 No 3 (2020): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v6i3.2894

Abstract— This paper presents a cooperation recommendation strategy between higher education institution. The recommendation is based on the contents of journals published in a university journal portal. As a case study, we concentrate our approach for the journals with information technology themes. All journals from 10 reputed universities will be compared by using keywords and the contents of the journal themselves. A partnering recommendation list is built by utilizing Latent Semantic Indexing (LSI). LSI technique is used to reduce the curse of dimensionality from the original data set and to generate topical analysis from all journals as semantic representation for each journals. Topic modeling is used to calculate the categorical similarity in the data set of each university journal and a search query. After all categorical similarities have been calculated, an average value of journal topics coherence is used to construct the final recommendation of partner candidates. This approach ensure that the final recommendation is based on the interest of each university rather than the frequencies of matched keywords in each journal.

BESKlus : BERT Extractive Summarization with K-Means Clustering in Scientific Paper Feliks Victor Parningotan Samosir; Hapnes Toba; Mewati Ayub
Jurnal Teknik Informatika dan Sistem Informasi Vol 8 No 1 (2022): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v8i1.4474

This study aims to propose methods and models for extractive text summarization with contextual embedding. To build this model, a combination of traditional machine learning algorithms such as K-Means Clustering and the latest BERT-based architectures such as Sentence-BERT (SBERT) is carried out. The contextual embedding process will be carried out at the sentence level by SBERT. Embedded sentences will be clustered and the distance calculated from the centroid. The top sentences from each cluster will be used as summary candidates. The dataset used in this study is a collection of scientific journals from NeurIPS. Performance evaluation carried out with ROUGE-L gave a result of 15.52% and a BERTScore of 85.55%. This result surpasses several previous models such as PyTextRank and BERT Extractive Summarizer. The results of these measurements prove that the use of contextual embedding is very good if applied to extractive text summarization which is generally done at the sentence level.

Title

Found 9 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 9 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 9 Documents
Search