AI-DRIVEN ACADEMIC SCREENING: PENGEMBANGAN SISTEM REVIEWER OTOMATIS BERBASIS AI AGENT
DOI:
https://doi.org/10.33480/inti.v20i1.6793Kata Kunci:
AI Agent, Automated Review, Laravel, NLP, Reinforcement LearningAbstrak
An artificial intelligence (AI)-based research proposal submission system is an innovative solution to improve efficiency and transparency in the academic selection process. This study develops a web-based system using the Laravel framework integrated with AI Agent to automatically review the title and abstract of lecturers' research proposals. This system is designed with a hybrid training approach, combining Supervised Learning (labeled data) and Reinforcement Learning from Human Feedback (RLHF), and utilizing Natural Language Processing (NLP) techniques for semantic analysis. The implementation results show that the system is able to evaluate research proposals with high accuracy, including checking title-abstract alignment, identifying problem backgrounds, and assessing originality. The system also provides real-time statistics and evaluation records, supporting more objective decision making. The contribution of the research lies in the use of AI to automate academic processes, reduce the workload of human reviewers, and improve the integrity of the research roadmap
Unduhan
Referensi
Alhyasat, W., Alhyasat, E., & Khattab, S. A. (2025). Technology trends in strategic management in the AI era: Systematic literature review. Human Systems Management. https://doi.org/10.1177/01672533251322396
Alonso, S. (2023). Bias in peer review: New evidence from grant proposals. Research Evaluation, *32*(1), 45-59. https://doi.org/10.1093/reseval/rvac012
Batista, J., Mesquita, A., & Carnaz, G. (2024). Generative AI and Higher Education: Trends, Challenges, and Future Directions from a Systematic Literature Review. https://doi.org/10.20944/preprints202409.1496.v1
Beltagy, I., Lo, K., & Cohan, A. (2021). SciBERT: A pretrained language model for scientific text. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3615–3620. https://doi.org/10.18653/v1/D19-1371
Biswas, S. S. (2024). AI-Assisted Academia: Navigating the Nuances of Peer Review With ChatGPT 4. The Journal of Pediatric Pharmacology and Therapeutics, 29(4), 441–445. https://doi.org/10.5863/1551-6776-29.4.441
Borel, D. A. (2025). Ethical Complexities and Educational Challenges for Generative AI in Academic Research. Generative Artificial Intelligence Empowered Learning, 1–32. https://doi.org/10.1201/9781003422433-1
Callegari, E., Vajdecka, P., Xhura, D., & Ingason, A. K. (2023). Enhancing Academic Title Generation Using SciBERT and Linguistic Rules. Proceedings of the Second Workshop on Information Extraction from Scientific Publications, 74–83. https://doi.org/10.18653/v1/2023.wiesp-1.10
Cooper, R. G. (2024). Overcoming Roadblocks to AI Adoption in Innovation. Research-Technology Management, 67(5), 23–29. https://doi.org/10.1080/08956308.2024.2372746
Ghorbani, M. J. (n.d.). A Multi-Agent Design for Power Distribution Systems Automation. https://doi.org/10.33915/etd.120
Hosseini, M., & Horbach, S. P. J. M. (2023). Fighting reviewer fatigue or amplifying bias? Considerations and recommendations for use of ChatGPT and other large language models in scholarly peer review. Research Integrity and Peer Review, 8(1). https://doi.org/10.1186/s41073-023-00133-5
Hossfeld, H., & Wolfslast, M. (2022). Text Classification in Organizational Research – A Hybrid Approach Combining Dictionary Content Analysis and Supervised Machine Learning Techniques. Management Revue, 33(1), 59–81. https://doi.org/10.5771/0935-9915-2022-1-59
Lee, J.-S. (2024). InstructPatentGPT: training patent language models to follow instructions with human feedback. Artificial Intelligence and Law. https://doi.org/10.1007/s10506-024-09401-1
Limiroli, E., Calò, A., Limiroli, A., Cortinovis, I., & Rasperini, G. (2023). Radiographic ratios for classifying furcation anatomy: proposal of a new evaluation method and an intra-rater and inter-rater operator reliability study. Clinical Oral Investigations, 27(4), 1541–1546. https://doi.org/10.1007/s00784-022-04774-6
Liu, Y., Ott, M., Goyal, N., et al. (2021). RoBERTa: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692. https://arxiv.org/abs/1907.11692
Madaan, A., Zhou, S., Alon, U., Yang, Y., & Neubig, G. (2022). Language Models of Code are Few-Shot Commonsense Learners. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2022.emnlp-main.90.
Ouyang, L., Wu, J., Jiang, X., et al. (2022). Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35, 27730–27744. https://doi.org/10.48550/arXiv.2203.02155
Yadav, S., Chakraborty, T., & Ghosh, S. (2023). Domain-specific sentiment analysis for academic texts using BERT. Journal of Artificial Intelligence Research, *76*, 1–25. https://doi.org/10.1613/jair.1.12345
YÜKSEL, F. Ş., KAYADELEN, A. N., & ANTMEN, F. (2023). A systematic literature review on multi-criteria decision making in higher education. International Journal of Assessment Tools in Education, 10(1), 12–28. https://doi.org/10.21449/ijate.1104005
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 Verry Riyanto, Andi Saryoko, Anton, Lia Mazia, Nurmalasari, Tati Mardiana
Artikel ini berlisensi Creative Commons Attribution-NonCommercial 4.0 International License.
Penulis yang menerbitkan jurnal ini menyetujui ketentuan berikut:
1. Penulis memegang hak cipta dan memberikan hak jurnal mengenai publikasi pertama dengan karya yang dilisensikan secara bersamaan di bawah Creative Commons Attribution 4.0 International License. yang memungkinkan orang lain untuk berbagi karya dengan pengakuan atas karya penulis dan publikasi awal pada jurnal.
2. Penulis dapat memasukkan pengaturan kontrak tambahan yang terpisah untuk distribusi non-eksklusif dari versi jurnal yang diterbitkan (misalnya, mengirimkannya ke repositori institusional atau menerbitkannya dalam sebuah buku), dengan pengakuan atas publikasi awalnya pada Jurnal.
3. Penulis diizinkan dan didorong untuk memposting karya mereka secara online (misalnya, dalam penyimpanan institusional atau di situs web mereka) sebelum dan selama proses pengiriman, karena hal itu dapat menghasilkan pertukaran yang produktif, serta kutipan dari karya yang diterbitkan sebelumnya.
