Claim Missing Document
Check
Articles

Found 2 Documents
Search

BERT Sentimen: Fine-Tuning Multibahasa untuk Ulasan Bahasa Indonesia Khen Dedes; Fatimatuzzahra; Hermansyah, Mas'ud; Setiawan, Akas Bagus; Pradana, Reza Putra; Harvyanti , Annisa Fitri Maghfiroh
Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Vol. 4 No. 2 (2025): September 2025
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i2.585

Abstract

Penelitian ini mengevaluasi pengaruh teknik augmentasi dan fine‑tuning terhadap kinerja model BERT multibahasa pada tugas klasifikasi sentimen ulasan film berbahasa Indonesia. Dataset awal terdiri dari 1.200 ulasan; 80% digunakan untuk pelatihan dan validasi (n = 960) dan 20% untuk pengujian (n = 240). Data pelatihan diperluas melalui augmentasi menjadi 2.880 sampel sintetis untuk keperluan fine‑tuning. Model kemudian di‑fine‑tune pada korpus yang diperluas dan dievaluasi menggunakan metrik akurasi, precision, recall, dan F1. Pada set pengujian diperoleh akurasi 82,5%, precision untuk kelas positif 76,0%, recall 95,0%, dan F1‑score 84,44%. Matriks kebingungan menunjukkan TP = 114, FN = 6, FP = 36, dan TN = 84, yang mengindikasikan sensitivitas tinggi terhadap ulasan positif namun terdapat proporsi false positive yang relatif besar. Temuan ini mengindikasikan bahwa augmentasi meningkatkan kemampuan model dalam menangkap sinyal positif (tingginya recall), namun memerlukan penyesuaian lebih lanjut untuk mengurangi kesalahan prediksi positif (meningkatkan precision). Secara keseluruhan, hasil penelitian menyediakan bukti bahwa BERT multibahasa mampu menangani tugas sentimen berbahasa Indonesia dengan performa memadai apabila didukung strategi augmentasi dan prosedur validasi yang tepat.
Prototype Development of IoT-Based Real-Time Smart Parking Monitoring System at Polije’s Second Campus in Bondowoso Ariyadi, David Juli; Hakim, Lukman; Mulyadi, Ely; Hermansyah, Mas'ud; Pradana, Reza Putra
International Journal of Technology, Food and Agriculture Vol. 3 No. 1 (2026): Pebruary
Publisher : P3M Politeknik Negeri Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25047/tefa.v3i1.6679

Abstract

The increasing number of activities and students at Campus 2 of the State Polytechnic of Jember has led to high vehicle usage, creating pressure on limited parking facilities. Current policies relying on manual verification of Vehicle Registration Certificates (STNK) still result in inefficiencies and security risks due to the lack of automated data recording. This research aims to develop an Internet of Things (IoT)-based Smart Parking System with real-time monitoring to address these challenges. The proposed system integrates RFID for rapid identification, while data is recorded in a real-time database (MySQL with API integration) and displayed through a web-based dashboard. A QR code-based STNK scanning mechanism is also incorporated to strengthen vehicle authentication. Based on the results of trials and implementation, the system is able to run optimally with the RFID sensor reading success rate reaching 100% at a distance of 1–2 cm. The database integration performance shows stable results, with the average data storage time in the database being approximately 3.86 seconds, which is still categorized as real-time. This prototype successfully improves data collection accuracy, enables real-time supervision, and provides statistical insights into parking utilization. In conclusion, the implementation of this IoT-based smart parking system is proven to reduce manual intervention, enhance operational efficiency, and support campus parking management that is more transparent, efficient, and measurable. This innovation contributes to the transition toward a smart campus and supports digital governance at Polije’s Second Campus in Bondowoso.