Claim Missing Document
Check
Articles

Reliable Intent Detection in Public Service Chatbots Using Hybrid IndoBERT and Bidirectional Long Short-Term Memory with Confidence-Based Decision Strategy Satya, Barka; Kurniawan, Mei Parwanto; Indryatmoko, Toto; As'adurrofiq, As'adurrofiq
Jurnal Teknik Informatika (Jutif) Vol. 7 No. 3 (2026): JUTIF Volume 7, Number 3, June 2026
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2026.7.3.5794

Abstract

The rapid digitalization of public services has increased the demand for intelligent information systems capable of providing accurate and responsive assistance to citizens on a 24/7 basis. However, many existing public service chatbots still rely on rule-based mechanisms or single-model natural language processing (NLP) approaches, which often fail to handle linguistic variations, informal expressions, and ambiguous user queries. This study proposes a Hybrid Natural Language Understanding (NLU) architecture that integrates a fine-tuned IndoBERT model with a Bidirectional Long Short-Term Memory (BiLSTM) network to improve intent detection performance in public service chatbots. To enhance system reliability, a confidence-based decision-making mechanism is introduced, enabling the system to dynamically select the most reliable prediction or activate a fallback pattern-matching module when confidence thresholds are not met. The proposed approach was evaluated on a custom dataset comprising 53 public service intents, spanning formal and informal Indonesian language use. Experimental results demonstrate that the hybrid architecture achieves an intent classification accuracy of 86.8%, outperforming single-model approaches while maintaining an acceptable response time for practical deployment, particularly in public service scenarios where accuracy and reliability are prioritized over response speed. Furthermore, integrating a continuous learning mechanism enables the system to adapt to low-confidence queries over time, thereby improving robustness in real-world applications. These findings indicate that hybrid NLP architectures with confidence-aware decision mechanisms offer a practical and scalable solution for intelligent public service chatbots.
DAMPAK PENJUALAN DI INDUSTRI KULINER DENGAN MENGGUNAKAN DIGITAL MARKETING rendy mahardika; M Suyanto; Mei P Kurniawan
JURNAL TECNOSCIENZA Vol. 6 No. 1 (2021): JURNAL TECNOSCIENZA
Publisher : JURNAL TECNOSCIENZA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51158/tecnoscienza.v6i1.597

Abstract

Abstrak – Pemasaran digital atau digital marketing merupakan metode memperkenalkan produk atau barang dengan cara memanfaatkan teknologi informasi sehingga produk yang dijual dapat di lihat seluruh orang di dunia. Metode ini juga berguna untuk pelaku usaha dalam membuat pemasran tepat sasaran karena target pasar sesuai dengan profile konsumen, kebutuhan konsumen, keinginan konsumen dan kebiasaan konsumen. Peran digital marketing dapat mempengaruhi kebiasaan konsumen untuk berbelanja, dengan adanya digital marketing konsumen yang mengakses dunia maya dapat melihat produk yang dipasarkan dan mempengaruhi keputusan membeli konsumen. Tujuan dari penelitian Analisa Pengaruh Konten Digital Marketing Dalam Meningkatkan Penjualan Industri Kuliner adalah mengetahui pengaruh konten digital untuk sosial media dan pengaruh dari digital marketing, terhadap penjualan di industri kuliner yang menjadi objek penelitian yaitu pok-pok chicken Yogyakarta, Sego Ambyar dan Relasi Coworkingspace dengan. Penelitian ini dilakukan dengan mengamati data penjualan konsumen dan respon konsumen terhadap promo yang dilakukan dengan media digital. Hasil penelitian berupa analisa pengaruh digital marketing dan konten digital terhadap penjualan khususnya di Pok-Pok Chicken Cabang Hartono Mall, Sego Ambyar dan Relasi Coworkingspace. Selain itu Penelitian ini akan memberikan rekomendasi dan saran yang berasal dari analisa pengaruh digital marketing dan konten digital. Variable Penelitian yang digunakan adalah E-WOM (Electronic Word Of Mounth) Kata Kunci: EWORM, Konten Digital, dan Pemasaran Digital
IT GOVERNANCE DESIGN IN IMPROVING THE QUALITY OF DATA AND INFORMATION SECURITY USING COBIT 2019 Bagus Setya; Alva Hendi Muhammad; Mei Parwanto Kurniawan
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 4 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i4.6509

Abstract

This study aims to enhance the quality of data and information security at PT XYZ by developing Information Technology (I.T.) governance based on the C.O.B.I.T. 2019 framework. Data and information security are of utmost importance for Business Continuity in the contemporary digital age, particularly for companies operating in the property development industry, such as PT XYZ. The selection of C.O.B.I.T. 2019 as the framework is based on its comprehensive approach to I.T. governance, encompassing areas such as planning and organizing, acquisition and implementation, delivery and support, and monitoring and evaluation. The objective of this research is to pinpoint deficiencies in existing I.T. governance procedures and provide suggestions for improved measures that may be implemented to strengthen data and information security. The study entails qualitative analysis conducted through comprehensive interviews with essential stakeholders and examination of pertinent documents. An action plan is established based on the findings, which entails deploying an I.T. governance team and formulating more stringent security standards. By implementing the I.T. governance plan derived from C.O.B.I.T. 2019, PT XYZ aims to enhance the quality of data and information security, thus bolstering the company’s long-term viability and expansion