Article Per Year (5 Year)
p-Index From 2021 - 2026
2.338
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering IAES International Journal of Artificial Intelligence (IJ-AI) Jurnal Ilmu Komputer dan Informasi Jupiter Berkala Ilmiah Pendidikan Biologi (BioEdu) Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Jurnal Teras Fisika : Teori, Modeling, dan Aplikasi Fisika Indonesian Journal of Electrical Engineering and Computer Science Reswara: Jurnal Pengabdian Kepada Masyarakat Law Development Journal Jurnal Publikasi Ilmu Komputer dan Multimedia
EVI YULIANTI
Faculty Of Computer Science, Universitas Indonesia
Religion Agriculture, Biological Sciences & Forestry Humanities Biochemistry, Genetics & Molecular Biology Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Social Sciences

Published : 16 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 16 Documents
Search

 1   2 
Expertise Retrieval Using Adjusted TF-IDF and Keyword Mapping to ACM Classification Terms Aini, Lyla Ruslana; Evi Yulianti
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 3 (2025): June 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i3.6397

Abstract

In an era of collaboration, knowing someone's expertise is becoming increasingly necessary. Recognizing individuals' proficiency can be challenging because it requires considerable manual time. This study explores the expertise of lecturers from the Computer Science Department, Universitas Indonesia (Fasilkom UI), based on scientific publications. The data were obtained from the Sinta journal website’s scrapping process, which includes Scopus, Garuda, and Google Scholar data sources. The approach used was keyword extraction using the adjusted TF-IDF. The resulting keywords were then mapped to the ACM classification class using cosine similarity calculations with various embedding models, including BERT, BERT multilingual, FastText, XLM Roberta, and SBERT. The experimental results highlighted that combining the adjusted TF-IDF with mapping to the ACM classes using SBERT is a promising approach for gaining the best expertise. The use of abstract data has proved to be better than that of full-text data. Using title-abstract-EN data achieved a score of 0.49 for both the P@1 and NDCG@1 metrics, whereas the title-abstract-ENID data attained a score of 0.75 for both metrics P@1 and NDCG@1.
Prediksi Harga Saham Menggunakan Empirical Mode Decomposition dan Feed Forward Neural Networks Saluza, Imelda; Mohammad Taufikurrahman; Lastri Widya Astuti; Hartati; Dhamayanti; Evi Yulianti
JUPITER (Jurnal Penelitian Ilmu dan Teknologi Komputer) Vol 15 No 2 (2023): Jurnal Penelitian Ilmu dan Teknologi Komputer (JUPITER)
Publisher : Teknik Komputer Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.10068884

Abstract

Stocks are a very market and shares are a characteristic of a company and their movements are influenced by the market. So if a company experiences problems, the company's shares may experience a spike. As happened with the Bank Syariah Indonesia (BSI) company which experienced service problems on the 8th to 20th. May 11, 2023, which caused a sharp decline in the company's shares. Volatile spikes can cause a risk of loss for investors and business people in the company. So both need to estimate their portfolio. Therefore, it is necessary to predict the share price, the closing price of BSI shares. This research uses time series data from the closing price of BSI shares, which is followed by decomposition using Empirical Model Decomposition (EMD) to break down the original data into several signals which then select these signals using Correlation Based Feature Selection (CFS) for feature selection and ends with make predictions using the Feed Forward Neural Networks (FFNN) algorithm. Based on the proposed model, the Mean Square Error (MSE) (training: 3.84E-02, testing: 1.73E-05) and Mean Absolute Error (MAE) (training: 1.48E-01, testing: 3.40E-03) values ​​are low for both training and testing data compared to without perform EMD and CFS from original data.
Analisis Pengukuran Kualitas Aplikasi Mobile Myjne Menggunakan Standar ISO 25010 Pada CV. Sukses Mandiri Perkasa Shela Agustini; Faradillah Faradillah; Evi Yulianti
Jurnal Publikasi Ilmu Komputer dan Multimedia Vol. 5 No. 2 (2026): Mei: Jurnal Publikasi Ilmu Komputer dan Multimedia
Publisher : Pusat Riset dan Inovasi Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jupikom.v5i2.7194

Abstract

Perkembangan teknologi informasi mendorong perusahaan logistik untuk memanfaatkan aplikasi mobile guna meningkatkan efisiensi dan kualitas layanan. MyJNE merupakan aplikasi resmi PT. Tiki Jalur Nugraha Ekakurir (JNE) yang digunakan oleh CV. Sukses Mandiri Perkasa dalam mendukung operasional pengiriman barang. Namun, masih ditemukan keluhan terkait performa dan kemudahan penggunaan aplikasi. Penelitian ini bertujuan untuk mengukur kualitas aplikasi MyJNE dari perspektif pengguna dengan mengacu pada standar ISO/IEC 25010, yang mencakup delapan karakteristik kualitas perangkat lunak: Functional Suitability, Performance Efficiency, Compatibility, Usability, Reliability, Security, Maintainability, dan Portability. Metode penelitian menggunakan pendekatan kuantitatif melalui penyebaran kuesioner berbasis skala Likert kepada 80 responden yang terdiri dari karyawan dan pelanggan CV. Sukses Mandiri Perkasa. Analisis data dilakukan menggunakan uji validitas, reliabilitas, statistik deskriptif, dan analisis GAP untuk membandingkan nilai harapan dan persepsi pengguna. Hasil penelitian menunjukkan bahwa seluruh indikator memiliki nilai GAP negatif, yang berarti kualitas aplikasi belum sepenuhnya memenuhi ekspektasi pengguna. Karakteristik dengan nilai GAP terbesar adalah Reliability, sedangkan Compatibility memiliki nilai GAP terkecil. Temuan ini merekomendasikan peningkatan pada aspek kestabilan sistem, kecepatan respon, dan perbaikan antarmuka guna meningkatkan kepuasan pengguna.
Sentiment Analysis of Tweets Before the 2024 Elections in Indonesia Using Bert Language Models Lenggo Geni; Evi Yulianti; Dana Indra Sensuse
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 3 (2023): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i3.26490

Abstract

General election is one of the crucial moments for a democratic country, e.g., Indonesia. Good election preparation can increase people's participation in the general election. In this study, we conduct a sentiment analysis of Indonesian public opinion on the upcoming 2024 election using Twitter data and IndoBERT model. This study is aimed at helping the government and related institutions to understand public perception. Therefore, they could obtain valuable insights to better prepare for elections, including evaluating the election policies, developing campaign strategies, increasing voter engagement, addressing issues and conflicts, and increasing transparency and public trust. The main contribution of this study is threefold: (i) the application of state-of-the-art transformer-based model IndoBERT for sentiment analysis on political domain; (ii) the empirical evaluation of IndoBERT model against machine learning and lexicon-based models; and (iii) the new dataset creation for sentiment analysis in political domain. Our Twitter data shows that Indonesian public mostly reacts neutrally (83.7%) towards the upcoming 2024 election. Then, the experimental results demonstrate that IndoBERT large-p1 is the best-performing model that achieves an accuracy of 83.5%. It improves our baseline systems by 48.5% and 46.49% for TextBlob, 2.5% and 14.49% for Multinomial Naïve Bayes, and 3.5% and 13.49% for Support Vector Machine in terms of accuracy and F-1 score, respectively.
From Text to Truth: Leveraging IndoBERT and Machine Learning Models for Hoax Detection in Indonesian News Muhammad Yusuf Ridho; Evi Yulianti
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 3 (2024): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i3.29450

Abstract

In the era of technology and information exchange online content being deceitful poses a serious threat to public trust and social harmony on a global scale. Detective mechanisms to identify content are essential for safeguard the populace effectively. This study is dedicated to creating a machine learning system that can automatically spot deceptive content in Indonesian language by utilizing IndoBERT. A model specifically tailored for the intricacies of the Indonesian language. IndoBERT was selected due to its capacity to grasp the linguistic nuances present, in Indonesian text which are often challenging for other models built upon the BERT framework. The key focus of this study lies in conducting an assessment of the IndoBERT model in relation to other approaches used in past research for identifying fake news like CNN LSTM and various classification models such as Logistic Regression and Naïve Bayes among others. To address the issue of imbalanced data between valid labels in fake news detection tasks we employed the SMOTE oversampling technique, for data augmentation and balancing purposes. The dataset employed consists of Indonesian language news articles publicly available and categorized as either hoax or valid following assessment by three judges voting system. IndoBERT Large demonstrated performance by achieving an accuracy rate of 98% outperform the original datasets 92% when tested on the oversampled dataset. Utilizing the SMOTE oversampling technique aided in data balance and enhancing the models performance. These outcomes highlight IndoBERTs capabilities in detecting fake news and pave the way for its potential integration, into real world scenarios.
Summarization of IndoSum dataset using enhanced TextRank with weighted word embedding Evi Yulianti; Piawai Said Umbara
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v15.i2.pp1919-1930

Abstract

This study evaluates the effectiveness of combining the TextRank method with word embedding on the Indonesian text summarization (IndoSum) dataset. Two experimental scenarios were applied: unweighted and weighted. The unweighted scenario incorporates word embedding, such as Word2Vec, FastText, and Indonesian bidirectional encoder representations from transformers (IndoBERT), into the TextRank framework. The weighted scenario further augments the term frequency-inverse document frequency (TF-IDF) weighting to the word embedding in the initial scenario. Our results on the effectiveness of enhanced TextRank using word embedding on IndoSum data are consistent with those reported in previous work on Liputan6 data. Both scenarios can significantly improve the effectiveness of TextRank summarization. Then, the weighted scenario showed performance improvement in most summarization systems compared to the unweighted scenario, with an average performance increase of 5.55% in recall-oriented understudy for gisting evaluation (ROUGE)-1 and 9.95% in ROUGE-2. This result confirms the robustness of the enhanced TextRank with weighted word embedding on the IndoSum data. Lastly, our study also highlights the importance of using domain-specific training data to optimize summarization performance.
Co-Authors Achmad Sulchan Agung Bambang Setio Utomo Aini, Lyla Ruslana Aris Haryadi Dana Indra Sensuse Dhamayanti Dhamayanti Dhamayanti Edi Suharyadi Evvy Kartini Faradillah Faradillah Hartati Imelda Saluza, Imelda Jatmiko Budi Baskoro Kartika Sari Lastri Widya Astuti Lenggo Geni Meganingrum Arista Jiwanggi Mohammad Taufikurrahman Muhammad Yusuf Ridho Nicholas Pangestu Nuzulul Khairu Nissa Piawai Said Umbara Rahadianti, Laksmita Shela Agustini sunardi sunardi Wihantoro Wihantoro