Article Per Year (5 Year)
p-Index From 2021 - 2026
5.745
P-Index
This Author published in this journals
All Journal Jurnal Algoritma Jurnal Teknologi Informasi dan Ilmu Komputer JAIS (Journal of Applied Intelligent System) CESS (Journal of Computer Engineering, System and Science) Sinkron : Jurnal dan Penelitian Teknik Informatika Jurnal Proaksi Jurnal Ekonomi Manajemen Sistem Informasi Jurnal E-Bis: Ekonomi Bisnis Jurnal Akuntansi dan Keuangan ARBITRASE: JOURNAL OF ECONOMICS AND ACCOUNTING International Journal of Management Science and Information Technology (IJMSIT) Journal of Management and Digital Business Jurnal Algoritma Malcom: Indonesian Journal of Machine Learning and Computer Science Literacy : International Scientific Journals of Social, Education, Humanities Jurnal Ilmiah MEA (Manajemen, Ekonomi, dan Akuntansi) Jurnal Teknologi Informasi RISTEC : Research in Information Systems and Technology Aktiva: Journal Of Accountancy and Management Journal of Knowledge Management Jurnal Pengabdian Masyarakat El-Mal: Jurnal Kajian Ekonomi & Bisnis Islam
Fikri Fahru Roji
Universitas Garut
Agriculture, Biological Sciences & Forestry Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Mathematics Social Sciences Other

Published : 44 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 44 Documents
Search

 1   2   3   4   5 
Analisis Sentimen Publik di X Terhadap Rencana Kenaikan PPN 12% Menggunakan Bert Ferdian Imawan; Diqy Fakhrun Shiddieq; Fikri Fahru Roji
CESS (Journal of Computer Engineering, System and Science) Vol. 10 No. 1 (2025): Januari 2025
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/cess.v10i1.65884

Abstract

Rencana kenaikan tarif Pajak Pertambahan Nilai (PPN) menjadi 12% telah menjadi salah satu isu kebijakan publik yang sedang diperbincangkan di masyarakat. Kebijakan ini memicu beragam tanggapan di media sosial X, yang mencerminkan adanya pro dan kontra terhadap rencana tersebut. Metode yang digunakan dalam penelitian ini adalah pre-trained BERT Classification yang digunakan untuk melakukan analisis sentimen, klasifikasi topik, serta memberikan akurasi tinggi. Tujuan penelitian ini untuk melalukan analisis sentimen dan memahami respon publik terhadap rencana kenaikan PPN 12%. Hasil analisis menunjukkan bahwa dominasi sentimen negatif sebesar 48,58%, yang mencerminkan kekhawatiran masyarakat terhadap potensi dampak kebijakan, diikuti oleh sentimen netral sebesar 42,39%, yang berfokus pada stabilitas ekonomi dan efek kebijakan secara umum. Sementara itu, sentimen positif sebesar 9,03%, merefleksikan optimisme terhadap manfaat kebijakan jangka panjang. Model BERT yang digunakan berhasil mencapai akurasi 83%, dengan nilai precision, recall, dan F1-score rata-rata sebesar 83%, 82%, dan 82%. Selain itu, visualisasi word cloud mendukung hasil analisis dengan menampilkan kata-kata dominan seperti “harga,” “rakyat,” dan “beban” pada sentimen negatif, serta “pajak” dan “daya beli” pada sentimen netral. Penelitian ini berkontribusi dalam menyediakan wawasan berbasis data untuk mendukung pemerintah dalam menyusun kebijakan mitigasi guna meminimalkan dampak negatif kebijakan.
Comparative Analysis of SVM and BERT for Sentiment and Sarcasm Detection in the Boycott of Israeli Products on Platform X Sabrina, Siti Sarah; Shiddieq , Diqy Fakhrun; Roji, Fikri Fahru
Sinkron : jurnal dan penelitian teknik informatika Vol. 9 No. 2 (2025): Research Articles April 2025
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i2.14723

Abstract

The Israel-Palestine conflict has triggered a global consumer movement, including a widespread boycott of Israeli-affiliated products in Indonesia. As this campaign gains momentum on digital platforms like X (formerly Twitter), understanding public sentiment becomes crucial—not only for gauging public opinion but also for anticipating potential socio-economic impacts. This study evaluates the effectiveness of two sentiment analysis models—Support Vector Machine (SVM) and Bidirectional Encoder Representations from Transformers (BERT)—in classifying sentiment and detecting sarcasm related to the boycott campaign. A total of 5,637 Indonesian-language tweets were manually labeled into positive, neutral, and negative categories, with sarcasm detection performed using a fine-tuned IndoBERT, model which classified tweets into two categories: sarcastic and non-sarcastic. The models were assessed using accuracy, precision, recall, F1-score, and computational efficiency. Results show that BERT outperforms SVM in both sentiment classification (accuracy: 69.26% vs. 64.58%; F1-score: 69.47% vs. 62.40%) and sarcasm detection (accuracy: 92.20% vs. 86.15%; F1-score: 92.38% vs. 85.27%). However, BERT requires significantly longer processing times 194.76 seconds for sentiment classification and 191.92 seconds for sarcasm detection, while SVM required only 18.81 seconds and 10.99 seconds. These findings highlight a trade-off between contextual comprehension and real-time efficiency. Future research may explore ensemble methods or threshold-tuning to optimize this balance. The practical implications of this research lie in its application for real-time public discourse monitoring and data-driven policy development. By improving the detection of nuanced expressions such as sarcasm, this study contributes to more accurate sentiment interpretation in polarized digital environments.
Analisis Sentimen Coretax: Perbandingan Pelabelan Data Manual, Transformers-Based, dan Lexicon-Based pada Performa IndoBERT: Sentiment Analysis of Coretax: A Comparison of Manual, Transformers-Based, and Lexicon-Based Data Labeling on IndoBERT Performance Rizkia, Agnia Suci; Wufron, Wufron; Roji, Fikri Fahru
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 5 No. 3 (2025): MALCOM July 2025
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v5i3.2151

Abstract

Analisis sentimen terhadap opini publik di media sosial menjadi tantangan signifikan karena kompleksitas bahasa informal dan volume data yang besar. Penelitian ini bertujuan untuk mengevaluasi pengaruh lima pendekatan pelabelan data manual, IndoBERT , IndoBERT weet, RoBERTa , dan InSet Lexicon terhadap performa model Indonesian Bidirectional Encoder Representations from Transformers (IndoBERT) dalam klasifikasi sentimen terkait isu Coretax. Sebanyak 8.035 tweet dikumpulkan, diproses, dan dilabeli menggunakan masing-masing pendekatan. Dataset hasil pelabelan kemudian digunakan untuk melatih ulang model IndoBERT, yang dievaluasi menggunakan metrik akurasi, F1-score, confusion matrix, dan kurva Receiver Operating Characteristic-Area Under the Curve (ROC-AUC). Hasil menunjukkan bahwa pelabelan otomatis menggunakan Indonesian Bidirectional Encoder Representations from Transformers for Tweet (IndoBERTweet) menghasilkan metrik tertinggi F1-Score (0,9802), tetapi mengalami dominasi kelas netral yang menunjukkan overfitting. Pelabelan manual menghasilkan distribusi kelas yang lebih merata meskipun dengan metrik lebih rendah F1-Score (0,8684), sedangkan Robustly Optimized BERT Pretraining Approach (RoBERTa) menunjukkan keseimbangan terbaik antara performa metrik dan distribusi label. InSet Lexicon dan IndoBERT menunjukkan kecenderungan bias terhadap kelas tertentu. Simpulan dari penelitian ini menegaskan bahwa efektivitas pelabelan tidak hanya ditentukan oleh skor metrik, tetapi juga oleh distribusi kelas yang seimbang untuk menghasilkan model yang adil dan dapat digeneralisasi.
Topic Modeling in Thesis Titles of Students from the Faculty of Economics Universitas Garut Using Latent Dirichlet Allocation Modeling Fahru Roji, Fikri; Rahayu, Dinar; Sabilul Muminin, Riyad; Ramdani, Dendi; Hendrik, Dede
RISTEC : Research in Information Systems and Technology Vol. 4 No. 1 (2023): JURNAL RISTEC : Research in Information Systems and Technology
Publisher : RISTEC : Research in Information Systems and Technology

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

Abstract

In higher education, the completion of a thesis within a 1 -year timeframe is a prerequisite for graduation. The selection of a thesistopic is influenced by personal interest, the expertiseof the thesis supervisor, and data availability. This research is designed to analyzethe thesis topics of Economics Faculty students at Garut University using the Latent Dirichlet Allocation (LDA) Modeling method. Utilizing quantitative and qualitative approaches, this research applies the concept of big data with techniques such as Data Crawling, Data Preprocessing, and Text Mining. The research successfully conducted topic modeling using the LDA method. The analysis showed that topic modeling with the LDA algorithm resulted in seven common thesis topics used in the students' thesis titles. With this, theresearch contributes to the understanding and efficacy in the determination of students' thesis topics. It is hoped that the results of this research can be utilized to assist in the efficient completion of theses.
Review Analysis of SatuSehat Application Using Support Vector Machine and Latent Dirichlet Allocation Modeling Fahru Roji, Fikri; Gia Ginasta, Nava; Cahyan, Yayan; Rahayu, Dinar; Ramdani, Dendi
RISTEC : Research in Information Systems and Technology Vol. 4 No. 1 (2023): JURNAL RISTEC : Research in Information Systems and Technology
Publisher : RISTEC : Research in Information Systems and Technology

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

Abstract

SatuSehat is a contact tracing application that replaces the PeduliLindungi application initiated by the Government of Indonesia with the aim of tracking the Covid -19 Virus. The success of the application can be known by analyzing sentiment reviews. In addition to the high number of reviews, there are also other things that need to be highlighted, namely the pattern of reviews that are not in accordance with refined spelling and diverse topics, so that identifying a topic from a collection of reviews is very difficult and takes a lot of time if done manually by humans. This research describes sentiment analysis and topic modeling on SatuSehat app user reviews. By applying Support Vector Machine (SVM) method for sentiment analysis and Latent Dirichlet Allocation (LDA) for topic modeling, this study reveals the views and trends expressed by users. The analyzed review data from Google Play Store includes 171,428 positive reviews and 131,246 negative reviews. The sentiment analysis results indicated the dominance of positive responses. LDA modeling resulted in 8 identified topics, from health concerns to app appreciation. However, negative topics included vaccination challenges, access issues, and app functionality. This research provides insight into users' perceptions of the SatuSehat app, providing a basis for further development and improvement of the app.
Conducting Penetration Testing to Identify Vulnerabilities in a Bank Company Information Technology Gia Ginasta, Nava; Krisnawanti; Fahru Roji, Fikri
RISTEC : Research in Information Systems and Technology Vol. 4 No. 2 (2023): RISTEC : Research in Information Systems and Technology
Publisher : RISTEC : Research in Information Systems and Technology

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

Abstract

Company XYZ is a regional business entity that manages finances and provides credit to small businesses. However, their e-banking applications have vulnerabilities that hackers can exploit. This research aims to identify and understand potential attacks on these vulnerabilities, assess the impact of exploitation by attackers, and provide recommendations for securing computer systems and networks based on penetration testing results. The XYZ e-banking application web server can be tested using five methods: Vulnerability Scanning, Apache Tomcat Sample Directory Vulnerabilities, Cross-Site Request Forgery (CSRF), Weak Cryptographic Testing, and Header Security. The application is in the Warning to High category, which indicates that it requires follow-up action. To mitigate the vulnerability, developers can take steps such as deleting the /examples directory, limiting the validity of cookies, using SSL and enabling Mod Security.
Design and Development of a Web-Based Community Service Information System at Garut University Sabilul Muminin, Riyad; Ramdani, Dendi; Fahru Roji, Fikri
RISTEC : Research in Information Systems and Technology Vol. 4 No. 2 (2023): RISTEC : Research in Information Systems and Technology
Publisher : RISTEC : Research in Information Systems and Technology

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

Abstract

The Community Service Program (KKN) is a mandatory activity in universities aimed at enhancing students' competencies in teamwork, leadership, and soft skills partnerships with the community. However, the implementation of KKN often faces challenges such as data inconsistencies, complex registration processes, and difficulties in activity management. This research aims to design and build a website-based KKN information system at Garut University to address these issues. By utilizing website technology, this system is expected to improve the efficiency and effectiveness of KKN implementation.This research employs the Unified Software Development Process (USDP) methodology, which is iterative and adaptive. The stages in USDP, namely inception, elaboration, construction, and transition, are followed systematically. In the inception phase, a needs analysis and feasibility study are conducted to determine the project scope. The elaboration phase produces the system architecture design and functional requirements specifications. The construction phase focuses on implementing the system according to the design that has been made. Finally, the transition phase includes testing, deployment, and system maintenance.The result of this research is a complete and functional website-based KKN information system. The system provides features such as online registration, group management, activity reporting, monitoring, and evaluation. System testing shows that this system is able to meet user needs and provide significant benefits in the implementation of KKN at Garut University. This system can also be an example for other universities that want to improve the quality of KKN implementation through the use of information technology.
Uncovering Hidden Sentiments and Topics in Online Lending Application Reviews with the Valence Aware Dictionary and sEntiment Reasoner (VADER) and Latent Dirichlet Allocation (LDA) Approaches Fahru Roji, Fikri; Ariesti Anggraeni, Windi; Sabilul Muminin, Riyad; Ramdani, Dendi; Cahyan, Yayan
RISTEC : Research in Information Systems and Technology Vol. 4 No. 2 (2023): RISTEC : Research in Information Systems and Technology
Publisher : RISTEC : Research in Information Systems and Technology

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

Abstract

Online lending (pinjol) has become an important part of the digital transformation of the financial sector, offering people easy access to funds. However, the increasing reliance on user reviews as a decision-making factor raises concerns about their authenticity and credibility. This research aims to analyze the sentiments and topics that appear in the reviews of Akulaku, Kredivo, and EasyCash lending apps on the Google Play Store. Using text mining techniques, VADER sentiment analysis, and LDA topic modeling, this research reveals dominant positive sentiments related to ease of use, service speed, and customer support. However, there were also negative reviews regarding loan application difficulties, technical issues, and bad experiences with billing and payments. This research provides valuable insights into the preferences and concerns of pinjol users, which can serve as a reference for service providers to improve the quality of their products and services.
Loyalitas Pengguna Aplikasi MyTelkomsel: Determinasi Kepuasan dan Kepercayaan Berbasis Customer Lifetime Value (CLV) Rendi Eka Herlinton; Rohimat Nurhasan; Fikri Fahru Roji
ARBITRASE: Journal of Economics and Accounting Vol. 6 No. 1 (2025): July 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/arbitrase.v6i1.2544

Abstract

This study aims to examine the influence of satisfaction and trust on Customer Lifetime Value (CLV) among users of the MyTelkomsel application. The research is motivated by the low level of user loyalty, despite the company’s efforts to introduce various digital features designed to enhance customer engagement. In the face of increasingly competitive digital service markets, understanding the key drivers of loyalty is essential. Employing a quantitative approach with an explanatory design, the study involved 100 purposively selected active users of the application. Data were collected through an online questionnaire using a four-point Likert scale and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The findings reveal that both satisfaction and trust have a significant positive effect on CLV, highlighting the importance of delivering a pleasant user experience and maintaining trust in the application's reliability to foster long-term loyalty. This research contributes to the theoretical framework of value-based loyalty and offers practical implications for telecommunications companies in developing adaptive relational marketing strategies in the digital era.
PEMILIHAN PROGRAM AFFILIATE MENGGUNAKAN PERSPEKTIF ANALYTICAL HIERARCHY PROCESS Almaiddah, Syinta; Kusmiati, Eti; Roji, Fikri Fahru
Jurnal Ilmiah Manajemen, Ekonomi, & Akuntansi (MEA) Vol 9 No 1 (2025): Edisi Januari - April 2025
Publisher : LPPM STIE Muhammadiah Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31955/mea.v9i1.4943

Abstract

Penelitian ini bertujuan untuk menganalisis faktor-faktor yang memengaruhi keputusan affiliator dalam memilih program affiliate pada platform Shopee dan Tik-Tok di Indonesia. Fokus penelitian ini adalah pada tiga kriteria utama: insentif finansial, sistem pembayaran, dan kemudahan penggunaan. Metode yang digunakan dalam penelitian ini adalah kuantitatif dengan pendekatan komparatif, di mana data dikumpulkan melalui kuesioner yang disebarkan kepada 100 responden yang merupakan affiliator di kedua platform tersebut. Teknik analisis data yang digunakan adalah Analytical Hierarchy Process (AHP) dengan bantuan perangkat lunak Expert Choice untuk menentukan prioritas kriteria yang mempengaruhi keputusan affiliator. Hasil penelitian menunjukkan bahwa insentif finansial, khususnya komisi dan bonus, menjadi faktor dominan dalam memilih program affiliate, diikuti oleh sistem pembayaran yang cepat dan aman, serta kemudahan penggunaan platform. Penelitian ini memberikan implikasi praktis bagi perusahaan dalam merancang dan meningkatkan program affiliate mereka, dengan fokus pada peningkatan insentif, sistem pembayaran yang efisien, dan kemudahan penggunaan platform. Penelitian ini juga menemukan bahwa platform yang menawarkan insentif yang lebih besar dan kemudahan dalam transaksi lebih menarik bagi affiliator.
Co-Authors AA Sudharmawan, AA Abdi Ilahi, Pyar Abdul Latip, Abdul Almaiddah, Syinta Anggraeni, Windi Ariesti Apriliya Nuraini, Raden Putri Arifah Nursadrina, Raisya Asri Mulyani Bekti, Surya Garian Dede Hendrik Dendi Ramdani Dewi Tresnawati Dinar Rahayu Dinar Rahayu Diqy Fakhrun Shiddieq Eri Satria Fakhrun Shiddieq, Diqy Fatimah, Nyinyi Ferdian Imawan Ghaida Farisya Hasbi S, Muhamad Husni Muharam Ihsanuddin Hasbi Al-ghifari Indri Tri Julianto Insani, Aura Intan Salamatuddaroen Kamila Syifa Ardiani Krisnawanti Kusmiati, Eti Lusiana Nur Safitri Marchella, Amanda Mega Silvia Moch. Rizky Cahyadiputra Muhammad Exsel Al Syiamudawan Muslim Al Kautsar Muslim Alkautsar Nava Gia Ginasta Novi Fauziah Novianti, Dea Nurmastin Nur Afni Hasna Anisya Nurhasan, Rohimat Permatasari, Rd Intan Puspita, Evi Putri Sukmana, Reinta Rahayu, Dinar Rahma Dianti, Ahrami Rahmawati . Ramdan, Galih Muhammad Rendi Eka Herlinton Ridian Gusdiana Ridwan Fauzi, Muhamad Ridwan Setiawan Ridwan Setiawan Rizkia, Agnia Suci Rohanudin, Muhammad Rohimat Nurhasan Sabda Ilahi, Perceka Sabilul Muminin, Riyad Sabrina, Siti Sarah Salamah, Susi Salman Fariz SALSABILA, ANNISA Shiddied, Diqy Fahrun Shiddieq , Diqy Fakhrun Shiddieq, Diqy Fakhrun Siti Nurhasanah Sri Meri Kurniawati Suci Lestari Taofiqurrohman, Hendra Wati Susilawati Wati Susilawati, Wati Wildan Hidayatul Hamdi Wufron Wufron Wulan Sri Utami Yaman Suryaman Yayan Cahyan