Article Per Year (5 Year)
p-Index From 2021 - 2026
5.336
P-Index
This Author published in this journals
All Journal Jurnal Informatika dan Teknik Elektro Terapan Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) IKRA-ITH Informatika : Jurnal Komputer dan Informatika IJID (International Journal on Informatics for Development) Jurnal Ilmiah Sinus TIN: TERAPAN INFORMATIKA NUSANTARA JPM: JURNAL PENGABDIAN MASYARAKAT Jurnal Responsif : Riset Sains dan Informatika Decode: Jurnal Pendidikan Teknologi Informasi Journal Computer Science and Informatic Systems : J-Cosys KERNEL: Jurnal Riset Inovasi Bidang Informatika dan Pendidikan Informatika Jurnal Pengabdian Masyarakat Bidang Sains dan Teknologi NUSANTARA: Jurnal Pengabdian Kepada Masyarakat Technologica SENTRI: Jurnal Riset Ilmiah Jurnal Keilmuan dan Keislaman INCOME: Indonesian Journal of Community Service and Engagement Journal of Artificial Intelligence and Digital Business Jurnal Saintifik JUSTIFY : Jurnal Sistem Informasi Ibrahimy Journal of International Multidisciplinary Research Journal of Data Analytics, Information, and Computer Science (JDAICS) Applied Information Technology and Computer Science (AICOMS) Cahaya Pengabdian Journal of Big Data Analytic and Artificial Intelligence Smatika Jurnal : STIKI Informatika Jurnal Jurnal Penelitian Sains Teknologi
Nova Tri Romadloni
Universitas Muhammadiyah Karanganyar
Religion Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Astronomy Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Neuroscience Nursing Physics Public Health Social Sciences Transportation Veterinary Other

Published : 40 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 40 Documents
Search

 1   2   3   4 
Uncovering Insights in Spotify User Reviews with Optimized Support Vector Machine (SVM) Nova Tri Romadloni; Wakhid Kurniawan
IJID (International Journal on Informatics for Development) Vol. 14 No. 1 (2025): IJID June
Publisher : Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2025.4903

Abstract

The rapid growth of user-generated reviews on platforms like Spotify necessitates efficient analytical techniques to extract valuable insights.  This study employs a Support Vector Machine algorithm, optimized using Forward Selection, Backwards Elimination, Optimized Selection, Bagging, and AdaBoost, to effectively classify user reviews. A dataset of approximately 10,000 Spotify reviews was compiled from diverse online sources, ensuring a representative sample. The analysis reveals sentiment patterns across positive, negative, and neutral categories, with positive reviews dominates the landscape. These patterns help highlight Spotify’s strengths while identifying areas for improvement. However, the SVM algorithm faces challenges in classifying minority classes, particularly negative sentiments, due to class imbalance. To address this, advanced optimization techniques are utilized to enhance classification precision and recall. Preprocessing steps, including data cleansing, tokenization, stemming, and stopword removal, refine the dataset, while TF-IDF converts text into numerical features for effective feature selection. The results show that the Optimized Selection method achieves the highest accuracy of 84.5%, outperforming other approaches. This research contributes significantly to developing balanced sentiment analysis models. Future studies may explore deep learning techniques to further improve classification accuracy and mitigate current limitations in data representation.
A Hybrid Approach of Pearson Correlation and PCA in Feature Selection for Opinion Mining Nova Tri Romadloni; Wakhid Kurniawan; Muhammad Yusuf Ariyadi; Burhan Efendi
IJID (International Journal on Informatics for Development) Vol. 14 No. 2 (2025): IJID December
Publisher : Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2025.5195

Abstract

This study proposes a hybrid feature selection approach that combines Pearson Correlation and Principal Component Analysis (PCA) to improve classification performance in opinion mining tasks. The rapid growth of e-commerce on social media platforms, such as TikTok, has generated a significant volume of user-generated reviews, which are valuable sources of consumer sentiment. However, the high dimensionality of textual data poses challenges in achieving accurate sentiment classification. To address this issue, the proposed method first applies Pearson Correlation to remove irrelevant features with weak correlation to sentiment labels, followed by PCA to reduce dimensionality. The dataset consists of user reviews from the TikTok Seller platform. Experiments using SVM, Naive Bayes, and Random Forest show that the hybrid approach achieves the highest accuracy of 86.2% (SVM and RF), improving over PCA-only by +0.9% and recovering 13.8% accuracy loss for Naive Bayes (from 72.0% to 83.1%). The results demonstrate that integrating correlation- and projection-based methods yields a more compact and effective feature set. This approach is especially suited for opinion mining in noisy, high-dimensional e-commerce data.
Evaluasi Kualitas Website PoliceTube dengan WebQual 4.0 Ammar Shafiy; Nova Tri Romadloni
JUSTIFY : Jurnal Sistem Informasi Ibrahimy Vol. 5 No. 1 (2026): JUSTIFY : Jurnal Sistem Informasi Ibrahimy
Publisher : Fakultas Sains dan Teknologi, Universitas Ibrahimy

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35316/justify.v5i1.9520

Abstract

This study examines the quality of PoliceTube.com from users' perspective using the WebQual 4.0 framework. This framework covers three dimensions — Usability Quality, Information Quality, and Service Interaction Quality — which were examined to determine which has the most influence on users' overall assessment. Data were collected via online questionnaire from 50 PoliceTube.com visitors selected through purposive sampling and analyzed using SPSS 26 through validity, reliability, Pearson correlation, and multiple linear regression tests. The instrument proved reliable with a Cronbach's Alpha of 0.877. All three WebQual dimensions positively correlated with Overall Quality, with Usability Quality being the strongest (r=0.502). The R Square value of 0.696 indicates that approximately 70% of the variation in overall quality assessment is explained by the three WebQual 4.0 dimensions. Notably, only the usability dimension had a significant individual impact based on partial testing. This suggests that PoliceTube.com visitors prioritize navigation ease and interface comfort over other aspects when assessing website quality. Therefore, administrators should focus on improving page layout, navigation clarity, and display consistency. Future research is recommended to expand the sample size and include additional variables such as user trust, content quality, or security perception for more comprehensive results.
Design and Development of a Web-Based Audit Clearance Letter Application System Using PHP Framework at the Karanganyar Inspectorate Wahyu Putri Sholefah; Nova Tri Romadloni
SMATIKA JURNAL : STIKI Informatika Jurnal Vol 16 No 02 (2026): SMATIKA Jurnal : STIKI Informatika Jurnal
Publisher : LPPM Universitas Bhinneka Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/smatika.v16i02.2330

Abstract

This research aims to design and develop a web-based Audit Clearance Letter application system at the Karanganyar Regency Inspectorate using the Laravel framework and MySQL database. The previous manual administrative process caused delays in verification, difficulties in tracking application status, and risks of data recording errors. This study adopted the Research and Development (R&D) methodology in conjunction with the Waterfall development model, which encompasses five sequential phases: requirements specification, system design, implementation, verification, and operational maintenance. The architectural foundation of the system was established upon the Model-View-Controller (MVC) pattern, selected to ensure a more organized, secure, and sustainable application structure. The results indicate that the system successfully integrates application submission, document upload, verification, letter issuance, and real-time status tracking within a single digital platform. Black Box Testing conducted on 14 testing scenarios achieved a 100% success rate and improved administrative efficiency from 2–3 working days to less than 1 working day in the verification and document monitoring process. In addition, User Acceptance Testing (UAT) achieved a User Satisfaction Index (USI) score of 88.2%, categorized as “Very Satisfactory.” The novelty of this research lies in the integration of a web-based Audit Clearance Letter administrative service specifically designed to improve transparency and efficiency in government supervisory institutions.
Analisis Sentimen Publik terhadap Kualitas BBM Pertamina pada Komentar Youtube Audy Trinugroho Listyawan; Nova Tri Romadloni
KERNEL: Jurnal Riset Inovasi Bidang Informatika dan Pendidikan Informatika Vol 7, No 1 (2026)
Publisher : Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.kernel.2026.v7i1.8852

Abstract

Pertamina merupakan perusahaan energi milik negara yang memiliki peran penting dalam penyediaan Bahan Bakar Minyak (BBM) di Indonesia. Kualitas BBM yang dihasilkan sering menjadi perbincangan publik, dan menimbulkan beragam tanggapan di media sosial. Penelitian ini bertujuan untuk menganalisis sentimen publik terhadap kualitas BBM Pertamina berdasarkan komentar Pengguna pada platform YouTube. Sebanyak 3.775 komentar dikumpulkan melalui web scraping dan dilabeli otomatis menggunakan model indonesian-roberta-base-sentiment-classifier yang mengelompokkan komentar kedalam dua kategori yaitu positif dan negatif. Proses analisis dilakukan dengan perangkat lunak RapidMiner dengan menggunakan dua algoritma Naïve Bayes dan Support Vector Machine (SVM). Tahapan analisis meliputi preprocessing teks (tokenizing, stopword removal, stemming) serta pembobotan TF-IDF. Evaluasi model dilakukan menggunakan 10-Fold Cross Validation dengan metrik Accuracy dan AUC sebagai indikator performa model. Hasil penelitian ini menunjukkan SVM memiliki performa lebih baik dengan akurasi 80,99% dan AUC 0,76, dibandingkan Naïve Bayes dengan akurasi 67,69% dan AUC 0,50. Analisis Sentimen memperlihatkan bahwa mayoritas komentar bersentimen negatif, yang mengindikasikan ketidakpuasan publik terhadap kualitas BBM Pertamina.
Sosialisasi Bijak Menggunakan Gadget untuk Edukasi Orang Tua dalam Mendampingi Anak Belajar Nova Tri Romadloni; Fatimah Hasna Karima; Mariyanto Mariyanto
ABDIKAN: Jurnal Pengabdian Masyarakat Bidang Sains dan Teknologi Vol. 4 No. 4 (2025): November 2025
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/abdikan.v4i4.6520

Abstract

The use of gadgets has become an essential part of daily life, including in supporting children’s learning processes. Gadgets provide wide access to information, interactive educational applications, and opportunities to develop digital skills. However, excessive use without proper guidance can lead to negative impacts such as physical health problems, digital addiction, decreased concentration, and reduced social interaction. These challenges highlight the crucial role of parents as guides, supervisors, and role models in ensuring wise gadget use. This community service program aimed to educate parents, particularly PKK mothers in Dawung Village, on practical strategies for accompanying children in their use of gadgets. The activities were carried out through socialization sessions, interactive discussions, and quizzes. The discussion revealed major issues faced by parents, such as difficulty in limiting screen time, children’s preference for gaming over learning, and limited knowledge of educational applications. Meanwhile, the quiz results indicated that most participants achieved “good” (45%) and “very good” (37.5%) categories, with an average score of 72, showing improved understanding after the program. This program concludes that family digital literacy can be strengthened through interactive socialization that actively involves participants. With consistent parental guidance, gadgets can be directed to become a healthy, productive, and safe learning tool for children’s development.
Implementasi Convolutional Neural Network dalam Mendeteksi Jenis Ras Kucing David Febrianto; Nova Tri Romadloni
Technologica Vol. 5 No. 2 (2026): Technologica
Publisher : Green Engineering Society

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55043/technologica.v5i2.580

Abstract

Klasifikasi ras kucing dari citra digital merupakan salah satu tantangan dalam bidang visi komputer karena adanya kemiripan fitur visual antar ras serta keterbatasan jumlah data pada setiap kelas. Penelitian ini bertujuan untuk mengimplementasikan Convolutional Neural Network (CNN) dalam proses klasifikasi ras kucing berbasis citra digital. Dataset diproses melalui beberapa tahap pra-pemrosesan, meliputi resize citra, normalisasi, dan augmentasi data untuk meningkatkan variasi data pelatihan. Model CNN dibangun menggunakan framework Keras dan TensorFlow dengan beberapa lapisan konvolusi, pooling, dan fully connected. Selain model CNN kustom, penelitian ini juga mengeksplorasi pendekatan transfer learning menggunakan arsitektur VGG16, ResNet50, dan MobileNetV2. Evaluasi model dilakukan menggunakan metrik akurasi, precision, recall, dan F1-score, serta didukung visualisasi Grad-CAM untuk membantu interpretasi prediksi model. Hasil eksperimen menunjukkan bahwa performa model CNN pada klasifikasi multi-kelas masih belum optimal akibat keterbatasan jumlah data dan tingginya kemiripan fitur visual antar ras kucing. Nilai evaluasi yang rendah menunjukkan bahwa model belum mampu melakukan generalisasi secara baik pada sebagian besar kelas. Penelitian ini menunjukkan bahwa ukuran dataset, distribusi data, dan jumlah sampel per kelas sangat memengaruhi performa CNN dalam klasifikasi citra multi-kelas. Oleh karena itu, penelitian selanjutnya disarankan menggunakan dataset yang lebih besar dan seimbang serta menerapkan optimasi arsitektur model dan fine-tuning untuk meningkatkan performa klasifikasi
Optimasi Feature Selection Pada Komentar Media Sosial Terhadap Peralihan Tv Digital Menggunakan Naïve Bayes, Support Vector Machine dan K-Nearest Neighbor Nova Tri Romadloni; Nisa Dwi Septiyanti
Decode: Jurnal Pendidikan Teknologi Informasi Vol. 3 No. 2: SEPTEMBER 2023
Publisher : Program Studi Pendidikan Teknologi Infromasi UMK

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51454/decode.v3i2.121

Abstract

Dalam menghadapi perubahan pada salah satu media informasi yaitu televisi yang semula menggunakan signal analog beralih menjadi TV dengan signal digital. Hal tersebut disebabkan bahwa siaran dengan transmisi analog rentan terhadap gangguan sehingga peralihan ini sebagai upaya dalam menikmati konten siaran televisi yang lebih baik. Namun, pada kenyataannya terdapat beberapa kesulitan yang dialami oleh beberapa pihak atau kalangan dengan berbagai alasan. Hal tersebut dapat diketahui melalui platform media sosial seperti twitter dan instagram. Dengan adanya kerjadian tersebut maka dapat diambil beberapa komentar positif dan negatif untuk mengetahui dampak dari peralihan signal digital tersebut. Dalam penelitian ini terdapat 1177 data komentar yang didapatkan sehingga membutuhkan teknologi untuk mendeteksi komentar tersebut positif atau negatif. Pada penelitian ini untuk optimasi komentar berbasis Pearson Correlation dengan menggunakan metode Naïve Bayes, Support Vector Machine (SVM) dan K-Nearest Neighbor (KNN). Hasil akurasi yang didapatkan dari ujicoba tersebut dengan metode Naïve Bayes 61,22%, SVM 80,10 %, dan KNN 79,93%. Jika ditambahan dengan Feature Selection mendapatkan hasil Naïve Bayes 63,68%, SVM 80,19%, dan KNN 80,02%. Berdasarkan hasil percobaan yang dilakukan digunakan untuk mengetahui berapa banyak perbandingan komentar positif dan negatif serta mengetahui perbandingan dari beberapa macam algoritma dengan seleksi fitur sehingga dapat menjadikan hasil yang optimal.
Analysis of Agile Concept Application in Lectures Conduction at UTM Jakarta and STIKOM CKI Miswanto; Nova Tri Romadloni
Decode: Jurnal Pendidikan Teknologi Informasi Vol. 4 No. 3: NOVEMBER 2024
Publisher : Program Studi Pendidikan Teknologi Infromasi UMK

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51454/decode.v4i3.639

Abstract

In today’s fast-paced tech world, it’s important to understand and adapt to new methods like Agile. Agile is commonly used in project and product management to help with planning, executing, monitoring, and completing projects based on user needs. This approach can also be applied in education, especially in classroom lectures. This research examines how Agile is used in lectures at UTM Jakarta and STIKOM CKI Jakarta. It looks at students’ understanding of Agile, their creativity during lectures, and the impact of a new curriculum on classroom learning. To analyse this, the study used descriptive statistics to measure students' understanding of Agile, a correlation test to see connections between different aspects of lectures, and a regression test to examine the new curriculum's impact. The goals are to 1) Measure students' understanding of Agile concepts. 2) Assess students' creativity in class, and 3) Analyze how curriculum changes affect classroom activities. Results show that students have a moderate understanding of Agile, and their creativity is evident in how they apply concepts, document work, and present material. The regression model shows that the new curriculum has a positive impact on classroom learning, and the findings are valid and reliable. Overall, Agile methods can enhance learning and creativity in the classroom.
NuminaMath 7B: Revolutionizing Math Solving with Integrated Reasoning Advanced Generative AI Tools and Python REPL Adi Jufriansah; Irwan Akib; Naufal Ishartono; Azmi Khusnani; Tanti Diyah Rahmawati; Edwin Ariesto Umbu Malahina; Osniman Paulina Maure; Nova Tri Romadloni
Jurnal Penelitian Sains Teknologi Vol. 2, No. 1, March 2026
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/saintek.v2i1.15728

Abstract

The efficacy of NuminaMath 7B, an AI model that was created to address mathematical challenges, is assessed in this investigation. We evaluated the model's accuracy and efficiency against conventional methods through experiments that produced quantitative data. Qualitative data were collected through surveys and interviews with users to gain insight into their experiences and pinpoint areas for improvement. The survey results indicated that users found NuminaMath 7B to be pertinent, effective, and user-friendly, as evidenced by the exceptionally high average scores in user experience (95), perception of features and interface (90), and additional feedback (85). NuminaMath 7B was able to offer mathematical solutions with logical and detailed explanations as a result of the model's development through two phases of adjustments, which were conducted using the Chain of Thought (CoT) methodology and inspiration from the Tool-Integrated Reasoning Agent (ToRA) framework. Testing demonstrated that the model achieved a score of 29 out of 50 in the AI Math Olympiad competition, despite encountering difficulties in resolving more intricate problems. This study underscores the significance and urgency of AI technology, particularly in the field of mathematics, as well as the significant potential of AI models to facilitate a more comprehensive comprehension of mathematical concepts.
Co-Authors Adi Jufriansah Ammar Shafiy Audy Trinugroho Listyawan Avianti, Risqi Nur Azmi Khusnani Budilaksono, Sularso Burhan Efendi Cucut Hariz Pratomo Cucut Hariz Pratomo David Febrianto Desi Lajar Sari Edwin Ariesto Umbu Malahina Efendi, Burhan Erwinda Sam Anafih Fanani, Galih Pramuja Inngam Fatimah Hasna Karima Hana Mulia, Pamela Handoko, Frendy Prasetyo Hani Setiani Hendri Setiawan Hilman F Pardede IMAM SANTOSO Irwan Akib Kurniaji, Ganno Tri Buana Kurniawan, Wakhid Lenny Puspita Dewi Mariyanto Mariyanto Mariyanto Miswanto Muhammad Ardiansyah Muhammad Irfan Luthfi Muhammad Qolbi Shobri Muhammad Syahriandi Adhantoro Muhammad Yusuf Ariyadi Mukhlis Mukhlis Mulia, Pamela Hana Mulyawati, Theana Lativa Nashiruddin, Abid Naufal Ishartono Nawwar, Nabil Abiyu Nisa Dwi Septiyanti Nova Ellyanza, Marcellina Nugraheni, Anidhya Siwi Nur Hayati Nurul Iksani, Salma Osniman Paulina Maure Pratomo, Cucut Hariz Primananda, Masdicka Maulana Rahmawati, Aderima Rauhulloh Ayatulloh Khomeini Noor Bintang Resi Intan Penatari Rianti , Ria Rika Putri Utami Saefudin Salma Nurul Ikhsani Samsi Samsi Sari, Desi Lajar Setyawati, Yayuk Sholefah, Wahyu Putri Sya’bani, Nur Hayati Tanti Diyah Rahmawati Tristanti, Novi Wahyu Putri Sholefah Wakhid Kurniawan Wakhid Kurniawan Wiwit Supriyanti YAN ADITYA PRADANA Yayu Sri Rahayu Yitno Puguh Martomo