Claim Missing Document
Check
Articles

Found 9 Documents
Search

Sentiment Analysis of Bapenda South Sulawesi Mobile Application on Google Play Store Using Support Vector Machine Burhan, Muhammad Ikhwan; Ali, Andi Nurfadillah; Auliyah, A. Inayah; Hading, Muhaimin
Journal of Mathematics and Applied Statistics Vol. 2 No. 2 (2024): December 2024
Publisher : Yayasan Insan Literasi Cendekia (INLIC) Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35914/mathstat.v2i2.244

Abstract

This study analyzes user sentiment toward the Bapenda Sulsel Mobile application, an e-government platform developed by the Regional Revenue Agency of South Sulawesi, Indonesia. The research aims to evaluate user feedback and identify areas for improvement to enhance user satisfaction. Using sentiment analysis, user reviews from Google Play Store were collected and classified into positive, negative, and neutral sentiments through the Support Vector Machine (SVM) algorithm. Preprocessing steps such as tokenization, stopword removal, and stemming were applied to prepare the data. Term Frequency-Inverse Document Frequency (TF-IDF) was used for feature extraction to enhance classification accuracy. The SVM model demonstrated an overall accuracy of 80%, achieving a high recall of 98% for positive reviews but only 40% for negative reviews, reflecting challenges in handling class imbalance. Results show that 72% of users expressed positive sentiment, praising the app’s functionality and ease of use. However, 28% of reviews were negative, citing issues like technical bugs and usability challenges The findings highlight the app’s strengths in delivering e-government services and its role in improving tax management. However, the significant proportion of negative feedback emphasizes the need for addressing user concerns. Recommendations include balancing the dataset, refining the SVM model, and prioritizing improvements based on user feedback. This study contributes to the broader understanding of applying sentiment analysis in evaluating e-government platforms and offers actionable insights for enhancing the user experience.
Comparative Analysis of Algorithms for Sensitive Outlier Protection in Privacy Preserving Data Mining Burhan, Muhammad Ikhwan; Ali, Andi Nurfadillah; Auliyah, A. Inayah; Hading, Muhaimin
Jurnal Tekno Kompak Vol 19, No 2 (2025): AGUSTUS (In Progress)
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/jtk.v19i2.4754

Abstract

Data mining is a crucial method in the realm of Big Data for extracting valuable predictive insights from extensive datasets. In the contemporary digital landscape, a significant difficulty is preserving individual privacy during data mining, particularly in safeguarding sensitive outliers that may harbour personal information. Outliers are data points that markedly diverge from the overall trend and frequently encompass very specialised or sensitive information. This paper examines the comparative efficacy of various clustering algorithms employed in outlier detection, specifically PAM (Partitioning Around Medoids), CLARA (Clustering Large Applications), CLARANS (Clustering Large Applications Based on Randomised Search), and ECLARANS (Enhanced CLARANS). This study aims to evaluate the efficacy of each algorithm in identifying outliers and to examine the usefulness of the employed privacy protection strategy, specifically the Gaussian Perturbation Random method. This experiment utilises two health datasets: the Diabetes Dataset from the National Institute of Diabetes and Digestive and Kidney Diseases and the Wisconsin Breast Cancer Dataset. The two datasets were chosen because to their multivariate features, which exhibit adequate data variation for outlier detection. The study's results indicate that the CLARA algorithm effectively identified a superior quantity of outliers compared to the other algorithms, with the diabetes dataset exhibiting the greatest count of outliers (65 outliers). The CLARA algorithm shown superiority in identifying outliers within extensive datasets due to the utilisation of a sampling methodology. Conversely, the PAM, CLARANS, and ECLARANS algorithms identified a same quantity of outliers in both datasets. ECLARANS shown superior time efficiency on the diabetic dataset, but CLARA demonstrated the highest efficiency on the breast cancer dataset. The Gaussian Perturbation Random technique was employed for preserving the identified sensitive outliers. The findings indicate that this strategy effectively maintains privacy while ensuring detection accuracy is not compromised. This method provides a dependable means of safeguarding individual privacy in health data mining, a domain characterised by significant privacy concerns.
PELATIHAN PENGELOLAAN WEBSITE SEKOLAH BAGI GURU TK SEBAGAI UPAYA TRANSFORMASI DIGITAL PENDIDIKAN Auliyah, Inayah; Ali, Andi Nurfadillah; Putriani, A. Ika; Hading, Muhaimin; Burhan, Muhammad Ikhwan; Tenrigau, Andi Faried; Syam, Akmal Baharuddin
GLOBAL ABDIMAS: Jurnal Pengabdian Masyarakat Vol. 5 No. 2 (2025): November 2025, GLOBAL ABDIMAS
Publisher : Unit Publikasi Ilmiah Perkumpulan Intelektual Madani Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51577/globalabdimas.v5i2.762

Abstract

TKIT Al-Azizi merupakan salah satu taman kanak-kanak yang ada di Kota Parepare, taman kanak-kanak merupakan sebuah lembaga pendidikan formal yang memiliki tujuan untuk mengembangkan potensi anak usia dini yang meliputi perkembangan fisik maupun psikis anak yang terdiri dari nilai agama dan moral, fisik motorik, bahasa, dan seni. Namun saat ini TKIT Al-Azizi Pare-Pare menghadapi tiga tantangan utama: (1) ketiadaan website sekolah, (2) keterbatasan SDM dalam penguasaan teknologi informasi (pembuatan/pengelolaan website), dan (3) minimnya pemahaman tentang peran website sebagai media informasi dan promosi. Kegiatan pengabdian ini bertujuan meningkatkan kompetensi guru dan tenaga kependidikan dalam pengelolaan website sekolah melalui pelatihan teknis dan pendampingan intensif berbasis LMS Moodle. Metode pelaksanaan meliputi: (1) workshop pembuatan website, (2) praktik langsung pengelolaan konten digital, dan (3) pendampingan berkelompok. Evaluasi menggunakan pre-test dan post-test terhadap 14 peserta menunjukkan peningkatan signifikan: pengalaman penggunaan website naik dari 28,6% menjadi 83,3% (+54,7%), minat kontribusi konten mencapai 100%, dan pemahaman website sebagai pusat sumber belajar meningkat menjadi 53,9%. Hasilnya, sekolah kini memiliki website operasional (tkitalazizi.sch.id) yang dikelola mandiri. Kesimpulan membuktikan model pelatihan terstruktur dengan pendampingan intensif efektif mendorong transformasi digital dan literasi digital guru.
Evaluation of Machine Learning Algorithm for Automatic Assessment of School Students' English Essay Ali, Andi Nurfadillah; Hading, Muhaimin; Suryabuana, Andi Sahra
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 1 (2026): Article Research January 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i1.15496

Abstract

The manual assessment of essays in English language learning often faces challenges related to objectivity and efficiency, especially on a large scale. With advancements in artificial intelligence technology, machine learning-based approaches have begun to be adopted to automate this process through Automated Essay Scoring (AES) systems. However, most existing AES models tend to rely solely on the final scores from the dataset without considering the structural quality of the writing, such as coherence between paragraphs. This study aims to evaluate the effectiveness of machine learning algorithms in assessing school students' essays by adding coherence features as predictor variables in a regression model. This approach uses linguistic feature representation techniques to explicitly build coherence indicators. The proposed model achieved a QWK improvement from 0.69 to 0.89 using SMOTE and coherence features. Meanwhile, human evaluation results showed that the pair of Rater 1 and Rater 2 achieved a QWK of 0.82, the pair of Rater 1 and Rater 3 scored 0.79, and the pair of Rater 2 and Rater 3 scored 0.81. These values indicate a high level of agreement among raters, suggesting that the assessment instrument used is stable. The main contribution of this study is introducing the coherence feature as an explicit predictor in the AES model, filling the gap not provided by standard datasets and proving that coherence improves model accuracy. This research provides practical benefits such as speeding up the evaluation process, reducing teachers' workload, and improving the objectivity and consistency of assessment in language education and evaluation.
Implementasi Pembelajaran Berbasis Kecerdasan Buatan Di Upt Sd Negeri 16 Parepare Muhaimin Hading; Radhiansyah Radhiansyah; Nurul Chairunnisa Noor; A. Syahrinaldy syahruddin; A. Inayah Auliyah; Andi Nurfadillah Ali; Muhammad Ikhwan Burhan; Muhammad Irsan
Abdimas Toddopuli: Jurnal Pengabdian Pada Masyarakat Vol. 6 No. 2 (2025): Volume 6, No 2, Juni 2025
Publisher : Universitas Cokroaminoto Palopo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30605/atjpm.v6i2.6311

Abstract

Pemanfaatan teknologi dalam pendidikan dasar menjadi semakin krusial di tengah perkembangan era digital dan Revolusi Industri 4.0. Kegiatan pengabdian ini dilatarbelakangi oleh pentingnya peningkatan literasi teknologi di lingkungan sekolah dasar, khususnya dalam pemanfaatan kecerdasan buatan (Artificial Intelligence/AI) untuk mendukung proses belajar mengajar yang lebih interaktif dan adaptif. Program ini dilaksanakan di UPT SD Negeri 16 Parepare dengan tujuan utama untuk mengimplementasikan pendekatan pembelajaran berbasis AI. Metode pelaksanaan meliputi pelatihan intensif kepada guru mengenai konsep dan praktik penggunaan AI, penerapan langsung AI dalam kegiatan pembelajaran di kelas, serta evaluasi untuk mengukur dampak kegiatan. Hasil kegiatan menunjukkan adanya peningkatan pemahaman dan keterampilan guru dalam mengintegrasikan AI ke dalam pembelajaran, serta meningkatnya minat dan partisipasi aktif siswa selama proses belajar. Kegiatan ini memberikan kontribusi positif dalam memperkenalkan transformasi digital di lingkungan sekolah dasar, serta berpotensi menjadi model replikasi untuk sekolah lainnya.
Peningkatan Kompetensi Kewirausahaan Siswa melalui Pelatihan Desain dan Digital Marketing Produk Kombucha di SMA Negeri 4 Parepare Ghea Brigitta Dotulong; Rosdiana Marzuki; Pasmawati Pasmawati; Muhaimin Hading; Nur Azisah Syam; Muzakkir Muzakkir; Nurandini Nurandini; Putri Maulidiyah Bundah; Siti Hajar
Abdimas Toddopuli: Jurnal Pengabdian Pada Masyarakat Vol. 7 No. 2 (2026): Volume 7, No 2, Juni 2026
Publisher : Universitas Cokroaminoto Palopo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30605/rx62xa10

Abstract

Kegiatan pengabdian kepada masyarkat ini bertujuan untuk meningkatkan kompetensi kewirausahaan siswa melalui pelatihan desain dan digital marketing produk kombucha di SMA Negeri 4 Parepare. Kegiatan ini dilatarbelakangi oleh pentingnya pengembangan keterampilan kewirausahaan dan pemanfaatan teknologi digital bagi siswa sebagai bekal menghadapi perkembangan dunia usaha di era digital saat ini. Pelaksanaan kegiatan dimulai dari praktik pembuatan kombucha, kemudian pemanfaatan teknologi dalam mendesain suatu produk dalam hal ini botol untuk kombucha agar memberikan daya tarik, serta materi mengenai pemanfaatan media sosial dalam mempromosikan suatu produk. Para peserta mengikuti rangkaian kegiatan secara aktif. Evaluasi kegiatan dilakukan melalui pre-test dan post test serta survei kepuasan peserta untuk mengukur tingkat pemahaman dan ketertarikan terhadap materi yang diberikan. Hasil kegiatan menunjukkan adanya peningkatan pemahaman kewirausahaan siswa yang terlihat pada peningkatan nilai rata-rata peserta dari 64,13 pada pre-test menjadi 80,00 pada post-test. Analisis menggunakan metode N-Gain juga menunjukkan bahwa rata-rata skor N-Gain peserta sebesar 0,83 atau 82,70% yang termasuk dalam kategori tinggi. Selain itu, tingginya partisipasi peserta dalam sesi diskusi menunjukkan adanya minat dan antusiasme peserta terhadap pengembangan produk kreatif dan pemasaran digital. Kegiatan ini diharapkan dapat menjadi langkah awal dalam menumbuhkan jiwa kewirausahaan siswa yang kreatif, inovatif, dan adaptif terhadap perkembangan teknologi.
Attention-Driven Contrastive Learning for the Identification of Rare Partial Discharge Signal in GIS Muhaimin Hading; Herviana Herviana; Muh. Ikhsan Amar; A. Syahrinaldy Syahruddin; Muhammad Irsan; Aulia Salsabila R.H
Journal of System and Computer Engineering Vol 7 No 3 (2026): JSCE: July 2026
Publisher : Universitas Pancasakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61628/jsce.v7i3.2664

Abstract

Gas-insulated switchgear (GIS) is a critical component in high-voltage power transmission systems, where partial discharge (PD) activity can indicate early-stage insulation defects. However, phase-resolved partial discharge (PRPD)-based fault diagnosis remains challenging due to noisy signals, perturbed measurement conditions, and severe class imbalance, particularly for rare floating-electrode defects. This study proposes an attention-driven contrastive learning framework for rare PD signal identification in GIS. PRPD data are represented as two-dimensional density matrices derived from phase angle, discharge magnitude, and occurrence count. The proposed framework applies PRPD-specific data augmentation, followed by ResUNet-based denoising, CBAM-based feature refinement, and supervised contrastive learning to improve feature separability among PD classes. The framework was evaluated using a public 550 kV GIS PRPD dataset containing corona-type, surface-type, floating-electrode-type, and noise classes. The results show that augmentation substantially improved robustness. When trained with raw data, the proposed model achieved 91.90% accuracy and 53.81% F1-score under the original test scenario, but decreased to 48.76% accuracy and 46.26% F1-score under IEC-perturbed testing. After augmentation, the model achieved 98.24% accuracy and 96.58% F1-score under the original scenario, and maintained 97.44% accuracy and 97.76% F1-score under IEC perturbation. These findings indicate that the proposed framework supports robust PRPD representation learning for GIS PD diagnosis under perturbed and imbalanced conditions.
Deepfake Audio Detection Using Hybrid Audio Spectrogram Transformer with Dual-Attention Feature Fusion and Bayesian Optimization Kusnaeni Kusnaeni; Muhaimin Hading; Zaitun Zaitun; Andi Oxy Raihan Machikami R; Afif Budi Andy B
Journal of Mathematics, Computations and Statistics Vol. 9 No. 3 (2026): Volume 09 Issue 03 (September 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/ja96za26

Abstract

Deepfake audio has become a serious threat to digital security due to its ability to generate highly realistic synthetic speech for malicious purposes such as impersonation, fraud, and social engineering. Despite the rapid advancement of deepfake generation technologies, audio-based detection remains relatively underexplored compared to image and video domains. Moreover, existing approaches largely rely on handcrafted features and conventional machine learning methods, which are often insufficient to capture complex temporal and spectral dependencies and often exhibit limited generalization to unseen deepfake generation techniques. This study proposes a novel framework that leverages log-Mel spectrogram representations to capture informative time–frequency characteristics of audio signals. The proposed model integrates a Hybrid Audio Spectrogram Transformer to model global dependencies through self-attention and is further enhanced by a Dual-Attention Feature Fusion mechanism to improve discriminative capability at both spatial and channel levels. In addition, Bayesian Optimization is employed to efficiently optimize hyperparameters, leading to improved model performance, faster convergence, and better generalization. Experimental results demonstrate that the proposed model achieves an accuracy of 93.60% and an AUC of 0.9724, indicating excellent discriminative performance. The model also achieves a high recall in detecting deepfake audio, highlighting its effectiveness in minimizing false negatives and improving robustness in real-world scenarios. These findings demonstrate that the proposed framework provides an effective and reliable solution for deepfake audio detection and offers significant potential for deployment in practical cybersecurity and digital audio forensic applications.
Feature Based Classification for Automated Essay Scoring Muhaimin Hading; Muhammad Ikhwan Burhan; Andi Nurfadillah Ali; A. Inayah Auliyah; Mardhiyyah Rafrin; Arliyanti Nurdin; Wiwit Melayu
JURNAL TEKNOLOGI DAN ILMU KOMPUTER PRIMA (JUTIKOMP) Vol. 8 No. 2 (2025): Jurnal Teknologi dan Ilmu Komputer Prima (JUTIKOMP)
Publisher : Fakultas Teknologi dan Ilmu Komputer Universitas Prima Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34012/jutikomp.v8i2.7397

Abstract

Essays play a crucial role in traditional assessments, but evaluating them accurately, efficiently, and fairly poses a major challenge for educators. Automated Essay Scoring (AES) aims to address this issue by leveraging computational techniques to support teachers in the grading process. This study explores a classification model to classify the score based on the feature we created. We incorporate additional features aligned with the ASAP 2.0 scoring rubric, such as Lexical Sophistication, Source Adherence, Novelty and Relevance, and a Semantic Disruption feature. These features are used to construct a distributed representation of essays, which is then input into a Support Vector Machine (SVM) model for holistic score prediction. The proposed model achieved a Quadratic Weighted Kappa (QWK) score of 0.8397, indicating a high level of agreement with human raters. The results demonstrate the effectiveness of combining rubric-informed features with a non-linear classifier. The findings can be implemented for educational settings, where the model can be utilized to provide scalable and consistent scoring support, reduce grading workload for instructors, and deliver timely feedback to students. By aligning with rubric-based criteria, the approach can also foster more transparent and constructive learning processes, helping students identify specific areas for improvement in their writing. While the model exhibits strong predictive performance, it also presents limitations related to interpretability and generalizability, especially across diverse writing prompts and domains.