Article Per Year (5 Year)
p-Index From 2021 - 2026
0.882
P-Index
This Author published in this journals
All Journal Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Jurnal AbdiMas Nusa Mandiri Decode: Jurnal Pendidikan Teknologi Informasi Indonesian Community Journal INOVTEK Polbeng - Seri Informatika
SY. Yuliani
Multimedia Nusantara University
Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Energy Engineering Environmental Science Languange, Linguistic, Communication & Media Mathematics Physics Public Health Social Sciences Other

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Sentiment Analysis E-Wallet Application Services Using the Support Vector Machine and Long Short-Term Memory Methods Mochammad Dzikri Arya Darmansyah; Anik Vega Vitianingsih; Anastasia Lidya Maukar; SY. Yuliani; Seftin Fitri Ana Wati
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/apedaz75

Abstract

The rapid growth of financial technology services in Indonesia has increased the volume of user reviews, yet their utilization for sentiment-based insights remains limited in the e-wallet sector. This study compares the effectiveness of Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) in classifying the sentiment of 3,185 DANA e-wallet reviews collected from the Google Play Store and Instagram. The research process includes text preprocessing, lexicon-based labeling, and feature extraction using TF-IDF for SVM and word embeddings for LSTM. Model evaluation is conducted using a confusion matrix based on accuracy, precision, and recall, without inferential statistical testing. The results show that LSTM outperforms SVM, achieving an accuracy of 86.66%, a recall of 81.86%, and a precision of 82.09%, while the best SVM variant with an RBF kernel attains an accuracy of 84.93%. This study contributes by identifying key service-related factors influencing user satisfaction and dissatisfaction and by providing practical, sentiment-based insights to support service quality improvement. The novelty lies in the multi-platform analysis of Indonesian e-wallet reviews and the direct comparison of classical machine learning and deep learning approaches without statistical hypothesis testing. These findings confirm the effectiveness of deep learning for sentiment analysis of unstructured Indonesian text.
LITERASI PEMBERDAYAAN PENDIDIKAN DAN KESETARAAN GENDER MELALUI WEBSITE NASYIATUL AISYIYAH KOTA TANGERANG SELATAN Dinar Ajeng Kristiyanti; SY Yuliani; Monica Pratiwi; Irmawati Irmawati; Monika Evelin Johan; Akhmad Hairul Umam; Tresya Meisel Adiputri; Maureen Audilia
Jurnal AbdiMas Nusa Mandiri Vol. 8 No. 1 (2026): Periode Januari 2026
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/abdimas.v8i1.6402

Abstract

Nasyiatul Aisyiyah Kota Tangerang Selatan (NA Tangsel) is a youth women's organization in Indonesia under the Muhammadiyah community organization whose administrators consist of young women aged 17-40 years whose activities focus on women, religion, society, and education who have actively supported gender equality and education through various programs. The problems faced by the NA Tangsel administrators are logistical challenges, funding, community resistance, and limited market reach, which affect the effectiveness of their programs to grow and advance in supporting education and gender equality. To overcome this, the community service (PKM) implementation team has collaborated with the NA Tangsel administrators to disseminate website technology that can be a solution to become a place for NA administrators to run their programs to be more independent, empowered with increased digital literacy, obtain sustainable income, and support advocacy and empowerment efforts. This initiative strengthens economic empowerment and family welfare through effective and efficient skills training and entrepreneurship programs. The method applied is Community Participatory Action Research (CBPAR), which combines knowledge and action in a way that involves NA Tangsel administrators as active partners in every stage of PKM activities. The results achieved were increased implementation of science and technology through digital skills and the effectiveness of NA management performance, as measured through pre-tests and post-tests, with the percentage rising from 87.5% to 100%.
Sentiment Analysis of User Reviews on Maxim Application Using the Long Short-Term Memory (LSTM) Methods Maria Ilona Junide Bria; Anik Vega Vitianingsih; Anastasia Lidya Maukar; SY. Yuliani; Pamudi Pamudi
Decode: Jurnal Pendidikan Teknologi Informasi Vol. 5 No. 3: NOVEMBER 2025
Publisher : Program Studi Pendidikan Teknologi Infromasi UMK

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51454/decode.v5i3.1257

Abstract

The technological developments have encouraged the emergence of app-based transportation services that are increasingly popular with the public, one of which is the Maxim app. Despite offering convenience in booking transportation and other services, this app still receives various reviews from users regarding service quality. User feedback is provided through the Maxim app review section available on the Google Play Store platform. Sentiment analysis is applied in this study to identify shortcomings in the Maxim app, to help developers improve service quality and understand user satisfaction. The research procedure it comprises several phases, including data collection, text preprocessing, determining sentiment labels, assigning weights to terms, and a classification process using the Long Short-Term Memory (LSTM) algorithm. This studi unlike previous studies that commonly used classical machine learning techniques including Naïve Bayes and SVM, or BiLSTM, this research applies an LSTM model with lexicon-based sentiment labeling to improve consistency and contextual understanding in sentiment classification. A confusion matrix was utilized to evaluate the model’s performance. Overall, 1,200 user reviews were gathered through web scraping techniques from June 2024 to June 2025. The sentiment classification process uses a lexicon-based method to categorize user reviews grouped into three sentiment classes: positive, neutral, and negative. The findings suggest that 762 reviews are labelled as positive, 157 as neutral, and 281 as negative. The LSTM method testing demonstrated excellent performance, achieved 95.21% accuracy, 97.22% precision, 84.02% recall, and an F1-score of 88.84%.
Strengthening Production Capacity and Business Management through Co-Creation as a Foundation for Digital Transformation in Community-Based Producer Groups Melissa Indah Fianty; Sy. Yuliani; Wanda Gema Prasadio Akbar Hidayat; Kannisa Adjani
I-Com: Indonesian Community Journal Vol 6 No 3 (2026): I-Com: Indonesian Community Journal (September 2026)
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/icom.v6i3.11091

Abstract

Limited organizational capacity and manual business management remain significant barriers to digital transformation in productive community enterprises. This community empowerment program aimed to strengthen the capacity of the Dewata Farm aquaculture group and the Mekar Lestari food processing group through knowledge transfer and co-creation as the foundation for digital transformation. The program employed a participatory approach consisting of needs assessment, workshops, mentoring, prototype design, and evaluation using a five-point Likert-scale questionnaire analyzed descriptively. The results indicated a very high level of partner acceptance and readiness for digital solution implementation, reflected by a Readiness for Prototype Implementation score of 4.92 and a Knowledge Transfer Effectiveness score of 4.91. In addition, the program produced functional system requirements and a prototype tailored to the operational characteristics of both partner groups. These findings demonstrate that participatory capacity building can enhance organizational readiness and establish a strong foundation for sustainable digital transformation in rural productive enterprises.
Deephoax Image Detection based on Deep Learning using Convolutional Neural Network Architectures SY Yuliani; Nasywa Naura Aulia
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 4 (2026): August 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i7403

Abstract

The rapid growth of generative artificial intelligence has increased the spread of deephoax images, creating significant challenges for digital security, public trust, and the reliability of online information. This study evaluates the performance of MobileNet and Xception architectures for classifying facial images into fact and hoax categories while analyzing different feature representation levels within the Xception architecture through an ablation-based fine-tuning strategy. The proposed framework consists of data preparation, model architecture design, training procedures, and performance evaluation using confusion matrix analysis and metrics such as accuracy, precision, recall, and F1-score. Two publicly available datasets, DeepDetect2025 and FF-GenAI were utilized to evaluate the robustness of the proposed models. Experimental results show that Xception consistently outperformed MobileNet across all evaluation metrics, with the Middle Level Layer configuration achieving the best performance at 99.71% accuracy and F1-score. The findings indicate that intermediate feature representations are the most effective for capturing structural inconsistencies, texture irregularities, and synthetic blending artifacts commonly found in AI-generated facial images. In contrast, low-level representations were less discriminative, while highly abstract semantic representations slightly reduced sensitivity to localized manipulation artifacts. Overall, this study demonstrates the effectiveness of Xception-based feature refinement for deephoax image detection and contributes to AI-based approaches for digital content verification, cybersecurity, and visual misinformation mitigation.      
Co-Authors Akhmad Hairul Umam, Akhmad Hairul Anastasia Lidya Maukar Anastasia Lidya Maukar Anik Vega Vitianingsih Anik Vega Vitianingsih Dinar Ajeng Kristiyanti Irmawati Irmawati Kannisa Adjani Maria Ilona Junide Bria Maureen Audilia Melissa Indah Fianty Mochammad Dzikri Arya Darmansyah Monica Pratiwi Monika Evelin Johan Nasywa Naura Aulia Pamudi Pamudi Seftin Fitri Ana Wati Tresya Meisel Adiputri Wanda Gema Prasadio Akbar Hidayat