AI-Based Chatbot for SPBE Document Management: A HybridForward Chaining and Transformer Approach
Authors
-
Ery Setiyawan Jullev Atmadji
Politeknik Negeri Jember, Jember, Indonesia
-
Ricky Dwi Setyawan
Politeknik Negeri Jember, Jember, Indonesia
-
Nanik Anita Mukhlisoh
Politeknik Negeri Jember, Jember, Indonesia
DOI:
https://doi.org/10.30812/bite.v8i1.6347Keywords:
Chatbot, Electronic-Based Government System (SPBE), Forward Chaining, IndoBERTQA, PDF Text Extraction, TransformersAbstract
Background: Digital government transformation requires efficient and integrated management of SPBE documents using
artificial intelligence (AI).
Objective: To develop an AI chatbot to solve the problems of manual searches, human error, and difficulties in extracting
text from complex PDF documents in SPBE.
Methods: The study combined Forward Chaining (for structured questions) and the IndoBERTQA Transformer model
(for open-ended questions). Text was extracted using PyPDF2. The evaluation used 150 question-context-answer data
pairs and two Forward Chaining scenarios.
Result: Forward Chaining produced fast and fixed responses, while IndoBERTQA provided more contextual answers
(Cosine Similarity of 0.730). However, the low F1-score (0.316) shows that prediction accuracy is still a major weakness
and needs priority improvement. The system successfully sped up information access, although it still struggles with
extracting tables and non-text elements.
Conclusion: Integrating both methods provides a good balance between the chatbot’s speed and flexibility. Further
development on dataset quality, model optimization, and document extraction is highly necessary to improve the system’s
accuracy.
Downloads
References
[1] I. Ubaedila, “AI Chatbot Implementation for Digital Public Service Transformation in Indonesia,” INSIGHT:
International Journal of Social Research, vol. 3, no. 2, pp. 70–81, 2025.
[2] I. Gemiharto, “Analysis of Personal Data Preservation Policy in Utilizing AI-Based Chatbot Applications
in Indonesia,” Medium, vol. 12, no. 1, pp. 63–78, Jun. 30, 2024. doi: 10.25299/medium.v12i1.17772
[3] G. Fauziyyah et al., “Risk Security Cyber in System AI -Based : Study Evaluative on Indonesian Government
Digital Infrastructure,” Journal of Artificial Intelligence Research, vol. 1, no. 2, pp. 80–89, Aug. 4, 2025.
doi: 10.64910/jouair.v1i2.15
[4] M. Mustainah, D. Haryono, dan N. Nuraisyah, “Strategies to Improve the Quality of Public Services with
Artificial Intelligence (AI) in Indonesia,” Qubahan Academic Journal, vol. 5, no. 1, pp. 429–446, Mar. 3,
2025. doi: 10.48161/qaj.v5n1a1262
[5] S. Sundari, N. Nonci, dan A. Sinrang, “Transformasi SPBE Menuju Smart Governance Berbasis Kecerdasan
Buatan Di Sidenreng Rappang,” Jurnal Administrasi Publik dan Pemerintahan, vol. 3, no. 2, pp. 119–127,
Nov. 30, 2024. doi: 10.55850/simbol.v3i2.106
[6] W. M. H. Sasmita, S. Sumpeno, dan R. F. Rachmadi, “Improving Government Helpdesk Service With
an AI-Powered Chatbot Built on the Rasa Framework,” Jurnal RESTI (Rekayasa Sistem dan Teknologi
Informasi), vol. 9, no. 2, pp. 393–403, Apr. 19, 2025. doi: 10.29207/resti.v9i2.6293
[7] C. A. Oktavia dan R. F. Pribadi, “Implementation of AI-Based Chatbots to Enhance Efficiency and
Transparency in Land Certification in Indonesia,” Tunas Agraria, vol. 8, no. 2, pp. 252–267, May 2, 2025.
doi: 10.31292/jta.v8i2.426
[8] A. He dan M. Abisado, “Text Sentiment Analysis of Douban Film Short Comments Based on BERT-CNNBiLSTM-Att Model,” IEEE Access, vol. 12, pp. 45 229–45 237, 2024. doi: 10.1109/ACCESS.2024.3381515
[9] L. Hadibrata dan T. H. Rochadiani, “Deteksi Potensi Menyontek Menggunakan Feedforward Neural
Network Pada Ujian Daring,” SINTECH (Science and Information Technology) Journal, vol. 7, no. 2,
pp. 92–100, Aug. 31, 2024. doi: 10.31598/sintechjournal.v7i2.1585
[10] G. Bachtiar, “Embedding Ethical AI in Digital Public Infrastructure: Strategic Governance Pathways for
Indonesia,” Journal of Infrastructure Policy and Management, vol. 8, no. 2, pp. 175–185, Nov. 15, 2025.
doi: 10.35166/jipm.v8i2.123
[11] R. Indriasari dan A. Syauket, “Sophia, a Female Robot with Artificial Intelligence in View of Sociology
of Government,” Krtha Bhayangkara, vol. 18, no. 1, pp. 181–196, Apr. 30, 2024. doi: 10.31599/krtha.
v18i1.1649
[12] Y. Yang et al., “Improving the RAG-based Personalized Discharge Care System by Introducing the
Memory Mechanism,” in 2025 IEEE 17th International Conference on Computer Research and Development
(ICCRD), Jan. 2025, pp. 316–322. doi: 10.1109/ICCRD64588.2025.10963086
[13] N. K. Wati dan I. Hanafi, “Artificial Intelligence (AI) in Public Policy Reform: Approaches, Challenges,
And Outcomes,” Jurnal Ilmu Administrasi: Media Pengembangan Ilmu dan Praktek Administrasi, vol. 22,
no. 2, pp. 172–185, Dec. 31, 2025. doi: 10.31113/jia.v22i2.1283
[14] K. Kaur dan P. Kaur, “BERT-CNN: Improving BERT for Requirements Classification using CNN,”
Procedia Computer Science, vol. 218, pp. 2604–2611, 2023. doi: 10.1016/j.procs.2023.01.234
[15] D. T. Speckhard et al. “Training speedups via batching for geometric learning: An analysis of static and
dynamic algorithms.” version 4, pre-published.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ery Setiyawan Jullev Atmadji; Ricky Dwi Setyawan, Nanik Anita Mukhlisoh
This work is licensed under a Creative Commons Attribution 4.0 International License.
