Article Per Year (5 Year)
p-Index From 2021 - 2026
0.947
P-Index
This Author published in this journals
All Journal TRANSISTOR Elektro dan Informatika JSHP (Jurnal Sosial Humaniora dan Pendidikan) Infotek : Jurnal Informatika dan Teknologi Walisongo Journal of Information Technology Populer: Jurnal Penelitian Mahasiswa JURNAL ILMIAH SAINS TEKNOLOGI DAN INFORMASI Journal of Computer Science and Information Technology Technema: Journal of Intelligent Engineering and Computing
Mustafa, Mustafa
Jurusan Teknik Informatika, Universitas Islam Sultan Agung
Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Social Sciences Other

Published : 14 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 14 Documents
Search

 1   2 
PENERAPAN NAÏVE BAYES UNTUK KLASIFIKASI PENYEDERHANAAN TEKS BACAAN ANAK DISLEKSIA Ika Rahmawati; Mustafa Mustafa
Journal of Computer Science and Information Technology Vol. 2 No. 4 (2025): September
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70248/jcsit.v2i4.2372

Abstract

Disleksia merupakan gangguan belajar spesifik yang ditandai dengan kesulitan dalam membaca, menulis, dan mengeja. Permasalahan yang sering terjadi pada anak disleksia adalah kesulitan dalam mengikuti Pelajaran di sekolah serta sulit membedakan huruf b dan d, n dan u, p dan d. penelitian ini dilakukan untuk membantu anak disleksia dalam menyederhanakan teks bacaan dari kalimat yang sulit menjadi kalimat yang sederhana maupun kompleks. Metode ini menggunakan algoritma Naïve Bayes untuk menyederhanakan teks bacaan. Melalui metode Naïve Bayes, teks dapat secara otomatis diubah menjadi versi yang lebih sederhana tanpa menghilangkan makna utama sehingga dapat dimengerti oleh anak disleksia. Hasil penelitian menunjukkan bahwa penerapan algoritma Naïve Bayes dalam menyederhanakan teks mampu mengklasifikasikan kata atau kalimat sulit menjadi lebih sederhana. Penyederhanaan teks bacaan sangat penting mengingat kesulitan yang dihadapi oleh anak-anak dengan disleksia. Mereka dapat menjadi lebih frustasi dan kehilangan keinginan untuk belajar karena teks yang sulit. Kemajuan dan modernisasi teknologi informasi dan komunikasi menghasilkan inovasi baru, termasuk sistem yang mudah dan praktis serta pelayanan yang lebih cepat. Dengan kemajuan teknologi, banyak anak mengalami gangguan belajar, yang berdampak buruk pada prestasi akademik mereka.
Implementation of the Indobert Model for Named Entity Recognition in Public Complaint Texts from the City of Semarang Yossi Rifky Shabara; Mustafa Mustafa
Technema: Journal of Intelligent Engineering and Computing Vol. 1 No. 3 (2026): Technema: Journal of Intelligent Engineering and Computing
Publisher : CV SCRIPTA INTELEKTUAL MANDIRI

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

Abstract

Public complaint management in public services continues to face challenges because complaint data are generally presented as unstructured text containing informal language, abbreviations, and Indonesian-Javanese code-mixing. These characteristics complicate the identification of essential information and the determination of appropriate destination agencies when complaints are processed manually. This study aims to analyze the capability of the IndoBERT model for Named Entity Recognition (NER) in extracting relevant entities from public complaint texts in Semarang City to support complaint routing. A quantitative experimental approach was employed through complaint data collection, BIO-scheme annotation, text preprocessing, IndoBERT fine-tuning, and model evaluation using Precision, Recall, and F1-Score. The dataset consisted of 1,066 complaint sentences containing four target entities: service, location, problem category, and time. Strict-chunk evaluation using seqeval showed that the best IndoBERT checkpoint, obtained at Epoch 3, achieved a Macro F1-Score of 0.62, with the highest performance for LAYANAN (F1=0.68) and the lowest for LOKASI (F1=0.56). Error analysis further indicated that entity-boundary shifts, category ambiguity, and lexical variation in local and informal expressions remained important factors affecting recognition performance. The findings demonstrate that IndoBERT can transform heterogeneous complaint narratives into structured entity information and provide a foundation for improving the efficiency of public complaint management and routing within smart governance systems.
Analisis Kesesuaian Peta Okupasi Skema Pengembang Web dengan Kebutuhan Kompetensi Lowongan Kerja Online Menggunakan Cosine Similarity Silvi Nurcahyaningsih; Mustafa Mustafa
JURNAL ILMIAH SAINS TEKNOLOGI DAN INFORMASI Vol. 4 No. 3 (2026): Juli : Jurnal Ilmiah Sains Teknologi dan Informasi
Publisher : CV. ALIM'SPUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59024/jiti.v4i3.2532

Abstract

This study analyzes the compatibility between competencies in the National Occupation Map (SKKNI) of the ICT sector under the Web Developer scheme and competency requirements found in online job vacancies in Indonesia. The study employs Natural Language Processing (NLP) with Multilingual BERT (mBERT) to generate semantic representations of competency-related texts and Cosine Similarity to measure their semantic similarity. The dataset consists of 18 competency units, 58 competency elements, and 157 Performance Criteria (Kriteria Unjuk Kerja/KUK) from the National Occupation Map, along with 255 online job vacancies collected from Jobstreet Indonesia and LinkedIn. In the similarity analysis, all Performance Criteria and Competency Elements were aggregated into separate text representations and compared with the text representation of each job vacancy. The results show a mean similarity of 0.792932 for the aggregated KUK and 0.800890 for the aggregated Competency Elements, categorized as Suitable and Highly Suitable, respectively. The similarity values ranged from 0.646282 to 0.940792 for the aggregated KUK and from 0.639456 to 0.947454 for the aggregated Competency Elements. Word occurrence analysis further identified C, API, and Java as the three most frequently required competencies, appearing in 65.10%, 48.24%, and 45.10% of the analyzed vacancies, respectively. These results indicate that the competencies represented in the National Occupation Map generally show a high level of semantic compatibility with competency requirements in online job vacancies.
Deteksi Cyberbullying pada Twitter menggunakan Distilbert dan (Explainable Ai) Shap Hadana Maulana; Mustafa Mustafa; Ghufron Ghufron
Populer: Jurnal Penelitian Mahasiswa Vol. 5 No. 3 (2026): September : Populer: Jurnal Penelitian Mahasiswa
Publisher : Universitas Maritim AMNI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58192/populer.v5i3.5517

Abstract

The prevalence of cyberbullying on Twitter demands a fast and transparent automated moderation system. This study designs an efficient and explainable binary cyberbullying detection system using DistilBERT and the SHAP-based Explainable AI (XAI) method. The dataset, sourced from Kaggle, consists of 13,169 raw data filtered into 12,548 clean tweets. Preprocessing was conducted without stemming and stopword removal to preserve the language's semantic context, setting a max_length of 48 tokens. The pre-trained distilbert-base-multilingual-cased model was evaluated on an 80% training and 20% testing data split, while model transparency was validated using SHAP's PartitionExplainer algorithm. Evaluation results show DistilBERT performed robustly, achieving 84% accuracy, 84% precision, 86% F1-score, and 88% recall in detecting bullying, with an Area Under Curve (AUC) score reaching 0.9207. Locally, SHAP evaluation proved that the model concentrated heavy penalty weights on abusive words like "brengsek". Globally, SHAP revealed a unique phenomenon where the most important features were dominated by neutral vocabularies such as "times. roman" and "pendidikan", which the model cleverly utilized as strong discriminative indicators to validate normal texts. In conclusion, the integration of DistilBERT and SHAP yields a classification system that is not only accurate and efficient but also transparent and logically reasoned.
Co-Authors Abdullah Muzakki Ayunda Miftakhul Laili Choirul Iman Dedy Kurniadi Ghufron Ghufron Hadana Maulana Ika Rahmawati Imam Hendi Susanto Imam Much Ibnu Subroto Jimsan Jimsan Moch Taufik Mochamad Abdul Basir Muhammad Qomaruddin Muhammad Qomarudin Mustafid Mustafid R Rizal Isnanto Silvi Nurcahyaningsih Sri Mulyono Yossi Rifky Shabara Yusaena Yusuf