Claim Missing Document
Check
Articles

A Multilingual Approach to Aspect-Based Sentiment Analysis on Gobis Suroboyo Application Reviews using LDA and SVM Puspitasari, Dianita; Wahyuni, Eka Dyar; Permatasari, Reisa
Aviation Electronics, Information Technology, Telecommunications, Electricals, and Controls (AVITEC) Vol 7, No 2 (2025): August
Publisher : Institut Teknologi Dirgantara Adisutjipto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28989/avitec.v7i2.3033

Abstract

The GOBIS application, developed by the Surabaya City Transportation Department, is a digital service designed to provide public transportation information and reduce traffic congestion. Despite having exceeded 100,000 downloads, the application has received numerous complaints from users, as reflected in the multilingual reviews on its platform. To ensure analytical consistency, this research focuses solely on reviews in Indonesian and English. Using Aspect-Based Sentiment Analysis (ABSA), this study employs Latent Dirichlet Allocation (LDA) for aspect identification and Support Vector Machine (SVM) for sentiment classification. The aim of this research is to determine the dominant aspects in user feedback and evaluate the effectiveness of the Support Vector Machine (SVM) model in classifying multilingual reviews. The research results show six main aspects that frequently appear in reviews, namely Application Features and Development, User Suggestions and Service Innovation, Error and Location Accuracy, Delay and Application Usability, Comfort and Service Quality, as well as Route Tracking and Vehicle Information. The Support Vector Machine (SVM) model, tested with 10-fold cross-validation, demonstrates consistent performance, achieving balanced metrics accuracy (74.16%), precision (73.76%), recall (73.54%), and F1-score (73.63%). This highlights its capability in handling multilingual sentiment analysis for application improvement.
Student Complain Information System (SIPMA) using the Laravel Framework at Handayani University Makassar Asriana, Rina; Sadli, Adi; Wahyuni, Eka Dyar
Sistemasi: Jurnal Sistem Informasi Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i3.5113

Abstract

The objective of this study is to provide an innovative solution to enhance communication between students and university administration by designing a student complaint management system. In this context, the system is designed to facilitate efficient and effective handling of student complaints. Through a web-based application, students can easily submit complaints anytime and anywhere using an internet-connected device. The key features of the developed system include online complaint submission, real-time notifications, complaint status tracking, and a complaint management system that enables university administrators to respond to and resolve issues more promptly. The success indicators of this system include a fast response time—where complaints can be processed quickly—and a high level of user satisfaction regarding the efficiency and ease of use of the system. In this study, we adopted the Waterfall development methodology due to its structured and systematic approach, which facilitates planning and testing at each stage of development. This method allows developers to focus on one phase at a time, reducing the risk of errors during implementation. Furthermore, the Laravel framework was chosen for its ease of management, Model-View-Controller (MVC) architecture—which separates application logic from the user interface—and robust security features to protect user data and system integrity. The results of this study demonstrate that a student complaint system can be successfully designed and implemented, offering an effective solution for complaint management in educational settings. With this system, communication between students and university staff is expected to improve, and issues can be resolved more efficiently.
KOMPARASI METODE LABEL POWERSET K-NN DAN ML-KNN DALAM KLASIFIKASI MULTI-LABEL CYBERBULLYING PADA KOMENTAR INSTAGRAM Nur Fadlilah, Imamah; Dyar Wahyuni, Eka; Peratasari, Reisa
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 9 No. 3 (2025): JATI Vol. 9 No. 3
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v9i3.13686

Abstract

Peningkatan kasus cyberbullying di media sosial, khususnya pada aplikasi Instagram dengan berbagai bentuknya dapat berdampak negatif pada korban. Fenomena ini menunjukkan perlunya metode yang efektif untuk mengidentifikasi dan mengatasi komentar berisi cyberbullying. Penelitian ini bertujuan untuk mendeteksi komentar yang mengandung cyberbullying menggunakan pendekatan klasifikasi multi-label. Metode yang digunakan memanfaatkan ekstraksi fitur teks menggunakan TF-IDF dengan kombinasi unigram, bigram dan trigram, serta dua pendekatan utama dalam klasifikasi multi-label yaitu Problem Transformation dengan Label Powerset KNN dan Algorithm Adaptation dengan ML-KNN. Data yang digunakan dalam penelitian ini diambil dari komentar sebuah postingan pada aplikasi Instagram, dan akan dibangun sebanyak enam model klasifikasi cyberbullying. Hasil Penelitian menunjukkan bahwa pendekatan ML-KNN dengan kombinasi unigram memiliki akurasi yang lebih tinggi dibandingkan Label Powerset KNN dalam mendeteksi komentar yang mengandung cyberbullying.
ANALISIS SENTIMEN BERBASIS ASPEK PADA RESPONS SURVEI OPEN-ENDED MENGGUNAKAN LDA, DAN SVM Rahmawati, Dian; Dyar Wahyuni, Eka; Satria Yuda Kartika, Dhian
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 9 No. 3 (2025): JATI Vol. 9 No. 3
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v9i3.13723

Abstract

Dalam sebuah acara seminar nasional, evaluasi kepuasan peserta menjadi aspek penting untuk menilai keberhasilan acara dan mengusulkan perbaikan di masa mendatang. Salah satu metode evaluasi yang umum digunakan adalah survei online, yang sering kali mencakup pertanyaan terbuka (open-ended) agar peserta dapat menyampaikan opini dan pengalaman mereka secara bebas. Namun, respons survei open-ended bersifat tidak terstruktur, sehingga analisis manual menjadi kurang efektif karena memerlukan banyak waktu dan rentan terhadap subjektivitas. Analisis mendalam terhadap respons survei open-ended diperlukan untuk memahami opini peserta mengenai kualitas acara. Penelitian ini bertujuan untuk mengklasifikasikan sentimen dan mengidentifikasi aspek utama dalam respons survei open-ended dari peserta seminar. Penelitian ini menggunakan Metode Latent Dirichlet Allocation (LDA) untuk topic modeling, dan Support Vector Machine (SVM) untuk klasifikasi sentimen. Hasil penelitian menunjukkan bahwa kombinasi SVM dan teknik resampling Synthetic Minority Over-sampling Technique (SMOTE) menghasilkan performa terbaik dengan akurasi 85%, Precision 0.78, Recall 0.88, dan F1-Score 0.81. Analisis LDA berhasil mengidentifikasi 9 topik utama yang mencerminkan aspek penting dalam respons peserta, dengan mayoritas sentimen yang ditemukan bersifat positif, terutama dalam topik Manfaat atau Materi.
REKOMENDASI PAKET MENU PADA KOPI MESRA ABADI MENGGUNAKAN ALGORITMA FP-GROWTH DAN K-MEANS Maulana Arrasyid, Nizar; Dyar Wahyuni, Eka; Anjani Arifiyanti, Amalia
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 9 No. 4 (2025): JATI Vol. 9 No. 4
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v9i4.14459

Abstract

Penurunan penjualan di Kopi Mesra Abadi, yang turun dari surplus 131,6% pada Oktober 2023 menjadi 37,96% pada Maret 2024, menunjukkan perlunya strategi promosi yang lebih relevan untuk mencapai target penjualan per bulan. Penelitian ini bertujuan untuk merancang strategi promosi yang lebih relevan dengan menggunakan analisis pola pembelian pelanggan dan menu yang sering dibeli bersamaan. Metodologi yang digunakan mencakup dua algoritma: FP-Growth dan K-Means Clustering. FP-Growth digunakan untuk menemukan Frequent Itemsets dan Association Rules guna mengidentifikasi kombinasi menu yang sering dibeli bersama. K-Means Clustering digunakan untuk mengelompokkan pelanggan ke dalam tiga klaster berdasarkan waktu pembelian di tiga sesi: Sesi 1 (09.00-13.59), Sesi 2 (14.00-16.59), dan Sesi 3 (17.00-23.59). Hasil penelitian menunjukkan bahwa pembagian pelanggan ke dalam klaster per sesi membantu merancang paket menu yang sesuai dengan preferensi mereka. Sebagai contoh, Sesi 1 Klaster 0 lebih memilih "Nasi Ayam Pedas" dan "Teh O" untuk makan siang, Sesi 2 Klaster 2 memilih "Nasi Ayam Telor Asin" dan "Nasi Goreng Mawut" untuk pulang kerja, dan Sesi 3 Klaster 2 memilih paket Executive Meeting dengan "Kopi Butter," "Kopi Karamel," dan "Kopi Baileys." Penerapan FP-Growth dan K-Means membantu merancang paket menu yang menarik dan mencapai target penjualan.
Pengembangan Aplikasi Manajemen Litabmas Pendanaan Mandiri dengan Pendekatan Hierarchical Model-View-Controller (HMVC) Wahyuni, Eka Dyar; Afandi, Mohamad Irwan; Putra, Agung Brastama
Computer Science (CO-SCIENCE) Vol. 4 No. 1 (2024): Januari 2024
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/coscience.v4i1.2965

Abstract

In higher education, overseeing the execution of litabmas activities is a challenging and error-prone task, particularly when done manually through the physical submission of documents. Information is not always readily available, archives are frequently lost or even damaged, and tracing Litabmas external responsibility (articles, journals, patents/IPRs, etc.) from earlier periods can be challenging. This article describes how the Waterfall approach was used to construct the Litabmas management application. The Hierarchical Model-View-Controller (HMVC) technique is used to build the code architecture during the coding process. By reducing intermodular dependencies, this method makes it easier for a team to design an application. This application was developed to facilitate the management of the full cycle of Litabmas activity implementation for users, from generating Litabmas master data to initiating the Litabmas period, submitting proposals, conducting evaluations, and reporting Litabmas outputs and outcomes. The application has been tested using the black box method, and as a result, 23 use cases from six levels of users —administrator, head of institutional research, researcher, reviewer, auditor, and general visitor access rights —have been generated. All of these usecase have 100% of the expected output produced by the application.
Eksplorasi Kepuasan Pengguna PayPal Digital Wallet di Indonesia: Pendekatan UTAUT 2 Laksono, Cindy Fitri; Maulana, Ribas Satria; Wahyuni, Eka Dyar; Wulansari, Anita
Jurnal Ilmiah Sistem Informasi Vol. 4 No. 3 (2025): November: Jurnal Ilmiah Sistem Informasi
Publisher : LPPM Universitas Sains dan Teknologi Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/c962xq65

Abstract

Technological developments and globalization encourage people to develop in the transaction process. Now, conventional technology is starting to be abandoned and switched to a digitalization system, thus strengthening the balance of trade on an international scale. As one of the global e-wallets, PayPal offers convenience in cross-border transactions, but there are not many studies that specifically evaluate the level of satisfaction of Indonesian users in the application of this service. This research focuses on analyzing the level of satisfaction of using PayPal in Indonesia in cross-border transactions and examining technology acceptance factors with the Unified Theory of Acceptance and Use of Technology 2 (UTAUT 2) method. Data were collected through distributing questionnaires to active PayPal users in Indonesia and analyzed quantitatively using structural regression methods (SEM/PLS). The results showed that perceived ease of use, usefulness, and trust have a significant influence on user satisfaction. In addition, UTAUT 2 variables such as performance expectations, effort expectations, social influence, and hedonic value also contribute to forming positive perceptions of using PayPal. The findings are expected to contribute to the development of an international digital payment system that is more responsive to the needs of users in Indonesia.
Klasifikasi Cyberbullying pada Komentar Instagram dengan Menggunakan Supervised Learning Akira Permata Ramadhani; Eka Dyar Wahyuni; Amalia Anjani Arifiyanti
Neptunus: Jurnal Ilmu Komputer Dan Teknologi Informasi Vol. 2 No. 2 (2024): Mei : Jurnal Ilmu Komputer Dan Teknologi Informasi
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/neptunus.v2i2.108

Abstract

Cyberbullying is an action related to the use of digital technology to intentionally hurt, humiliate or bully other people online. This research focuses on the classification of cyberbullying comments on social media, especially Instagram comments, where many parties who then become a group of people who don't like something will come together to provide negative opinions and comments, which can cause lowered self-confidence and other bad impacts for other users and account owner. Therefore, a classification of Instagram comments regarding cyberbullying was carried out as an effort to prevent this action. The data used in this research is 2000 data, where this data will go through various processes so that it can be executed. In this research, the Naïve Bayes method was used by dividing two classes, namely Bully and Not Bully. Based on the results of the tests that have been carried out, the results obtained are an accuracy value of 84%, a precision value of 84%, a recall of 84%, and an f1-score of 84%.
Rancang Bangun Gamifikasi Latihan Mandiri Siswa SMA dengan Genre RPG Rulyawan, Muhammad Rizky Abiwafa; Wibowo, Nur Cahyo; Wahyuni, Eka Dyar
Innovative: Journal Of Social Science Research Vol. 5 No. 1 (2025): Innovative: Journal Of Social Science Research
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/innovative.v5i1.18080

Abstract

Penggunaan teknologi dalam dunia hiburan telah berkembang pesat, termasuk penerapan gamifikasi dalam pendidikan. Penelitian ini bertujuan untuk merancang dan membangun aplikasi edukasi berbasis Role-Playing Game (RPG) dengan mekanik turn-based untuk meningkatkan motivasi belajar siswa SMA. Aplikasi ini dikembangkan menggunakan metode Multimedia Development Life Cycle (MDLC) yang meliputi enam tahap: concept, design, material collecting, assembly, testing, dan distribution. Aplikasi ini menggunakan atribut pada karakter yang disesuaikan dengan mata Pelajaran tertentu seperti Health Point (HP) pada biologi, Attack (ATK) pada matematika, Mana Point (MP) pada kimia, Defence (Def) pada Bahasa Indonesia, Crit Rate pada Matematika Peminatan, dan Critical Damage (Crit DMG) pada fisika. Siswa dapat menyelesaikan 5 level utama ditambah dengan level tambahan Level EX). Aplikasi dirancang berbasis website menggunakan JavaScript, HTML, dan CSS dengan fitur utama seperti atribut karakter, latihan soal berbasis soal UTBK, dan pertempuran melawan mob. Hasil penelitian menunjukkan bahwa gamifikasi latihan soal dengan genre RPG dapat meningkatkan motivasi belajar siswa. Pengujian pada 10 siswa selama 15 hari dimulai dari tanggal 22 Oktober 2024 sampai 5 November 2024 menunjukkan bahwa 9 dari 10 siswa merasa termotivasi untuk berlatih soal dengan menggunakan aplikasi game, dengan 5 siswa mencapai level tertinggi (Level EX). Hasil penelitian ini menunjukkan bahwa pendekatan gamifikasi berbasis RPG mampu menciptakan pengalaman belajar yang interaktif, menyenangkan, serta membantu siswa meningkatkan motivasi belajar secara mandiri.
Parent Module in the Handayani University Makassar Information System Website using Laravel Framework Rumonang, Datu; Anatasya, A Edet Fauri; Wahyuni, Eka Dyar
Sistemasi: Jurnal Sistem Informasi Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i3.5191

Abstract

This study aims to develop a web-based academic information system at Handayani University Makassar that enables parents to directly monitor their children's academic progress. The system addresses previous limitations, where academic information was only accessible to students, thereby reducing parental involvement. This system includes features that enhance transparency and communication effectiveness between the university and parents, such as access to Study Plan Cards (KRS), automated notifications, and payment status monitoring. The system was developed using the waterfall method, which includes the stages of analysis, design, coding, and testing. The Laravel framework was chosen for its Model-View-Controller (MVC) architecture, data security, and ease of management. As a web-based system, it can be accessed anytime and anywhere via internet-connected devices. The results indicate that the system successfully supports students’ academic success by improving transparency, parental engagement, and communication with the university. With its comprehensive features and user-friendly design, the system offers an innovative solution that promotes a more inclusive and informative academic environment in the digital era.
Co-Authors Abdul Rezha Efrat Najaf Adam Rachman, Muhammad Adelia Putri, Ledina Adha, Didan Rizky Adimas Syiraa Setiabudhi Afandi, Mohamad Irwan Afandi, Mohammad Irwan Agung Brastama Putra Agung Brastama Putra Agussalim, Agussalim Agussalim, Agussalim Ahmad Galih Nur Jati Aji, Dwi rachmat Akira Permata Ramadhani alathoillah, abdul hanif Allendra Donny Irawan Amalia Anjani Arifiyanti Anastasya Nurhaliza, Zabina Anatasya, A Edet Fauri Andhika Rizky Aulia Anisa Rahma Salsabila Anjani, Amalia Apriandi, Dwatra Arfianto, Ricky Arief Yahya Prasetio Ariyana, Denny Arsya Amalia Ristias AryaRafa, Daud Asif Faroqi Asriana, Rina Atmaja, Ferdy Aulia, Ervina Rosa Bella Trinanda Sanni Cahyo Wibowo, Nur Candra, Devilia Dwi Dayu Renita Deswita Rini, Ni Made Berliana Devilia Dwi Candra Dharmawan, Ega Dhian Satria Yudha Kartika Diajeng Putri Widiastuti Dian Rahmawati Dian Rahmawati Doddy Ridwandono Doddy Ridwandono Eklesia Simaremare Ervina Rosa Aulia Fadiyah Dhara Al Arsya Fariz Febriany, Asri Kinanti Firdaus, Renanda Auzan Haidar Triari Respati harby, muhamad faiz Hayaza, QONITA Hilman Habib Habibi, Muhammad Icha Sinaga Imam Hanafi Irawan, Allendra Donny Irwan Afandi, Mohamad Irwan Afandi, Mohammad Izzuddin, Muhammad Kusumantara, Prisa Marga Kusumantara, Prisa Marga Kusumantara, Prisa Marga Laksono, Cindy Fitri Lina Wardani Lumintang, Qolbi Adi Marga Kusumantara, Prisa Mas'udah, Erica Mashita Kustyani Maulana Arrasyid, Nizar Maulana, Ribas Satria Mochammad Nabil Nugraha Ramadhan Mohamad Irwan Afandi Mohamad Irwan Afandi Muh. Ahlun Nazar Muhammad Farhan Najaf, Abdul Rezha Efrant Nendra Wono, Lasmargo Ni Made Berliana Deswita Rini Nur Cahyo Wibowo Nur Cahyo Wibowo Nur Cahyo Wibowo Nur Fadlilah, Imamah Nur Jati, Ahmad Galih Oktaviarini, kamilia nabila Peratasari, Reisa Permatasari, Reisa Permatasari, Reisa Prabowo, Dimas Agung Prabowo Prasetyo, Bagus Rizky PUSPITASARI, DIANITA Putra, Agung Brastama Qolbi Adi Lumintang Rachman Esa Masthury Budoyo Respati, Haidar Triari Ridwandono, Doddy Ristias, Arsya Amalia Rizka Hadiwiyanti Rulyawan, Muhammad Rizky Abiwafa Rumonang, Datu Sadli, Adi Safitri Pradhistya Suwandi Salma, Marylda Sanni, Bella Trinanda Sari, Reisa Permata Satria Yuda Kartika, Dhian Seftin Fitri Ana Wati Sembilu, Nambi Sugiarto Tri Luhur Indayanti Sugata Wajendra Dewi, Marylda Salma Wardani, Lina Wati, Seftin Fitri Ana Wibowo, Nur Cahyo Wicaksono, Yeni Windy Fadhilah Susanti Wulansari, Anita Yasmine Shalsabilla, Syafierra Yuniar, Sella