Article Retrieval And Automatic Summarization System Using BERT-Based Neural Network Model On Chatbot
DOI:
https://doi.org/10.52436/1.jutif.2026.7.1.4463Keywords:
Auto Summarization, BERT, Chatbot,, Cosine Similarity, Information Retrieval, NLPAbstract
The rapid growth of online scientific publications presents challenges in efficiently filtering relevant information. Many search systems still rely on keyword matching, which is often ineffective in understanding the context of user queries. This study develops a chatbot system based on BERT (Bidirectional Encoder Representations from Transformers) for scientific article retrieval and automatic summarization. The system is designed to comprehend user intent and generate summaries of relevant articles. The evaluation was conducted on a dataset of 506 scientific articles, assessing search accuracy based on topic, abstract, author name, and time range. Results show 100% accuracy in searches by author and abstract, with varying performance in topic-based and time-based searches. This system is expected to enhance the efficiency and relevance of scientific literature retrieval and support the productivity of researchers across various fields.
Downloads
References
Dhian Nur Rahayu and Lila Setiyani, “Systematic Literature Review: Delone and Mclean Model using VOSViewer on Google Scholar Database Case Year 2010-2020,” Int. J. Sci. Technol. Manag., vol. 3, no. 1, pp. 22–30, Jan. 2022, doi: 10.46729/ijstm.v3i1.402.
R. E. Ogunsakin, O. Ebenezer, M. A. Jordaan, M. Shapi, and T. G. Ginindza, “Mapping Scientific Productivity Trends and Hotspots in Remdesivir Research Publications: A Bibliometric Study from 2016 to 2021,” Int. J. Environ. Res. Public. Health, vol. 19, no. 14, p. 8845, Jul. 2022, doi: 10.3390/ijerph19148845.
H. Karlstrøm, D. W. Aksnes, and F. N. Piro, “Benefits of open access to researchers from lower-income countries: A global analysis of reference patterns in 1980–2020,” J. Inf. Sci., p. 01655515241245952, Apr. 2024, doi: 10.1177/01655515241245952.
H. Y. Hasibuan, Y. Yuhana, C. A. H. F. Santosa, S. Syamsuri, and U. Wahyudin, “MENYELISIK PENELITIAN TERKAIT DIAGNOSTIK KOGNITIF MATERI MATEMATIKA DI INDONESIA MELALUI SYSTEMATIC LITERATURE REVIEW,” AKSIOMA J. Program Studi Pendidik. Mat., vol. 12, no. 2, p. 1762, Jun. 2023, doi: 10.24127/ajpm.v12i2.6886.
N. Minh Giam, N. Thi Hoai Nam, and N. Van Doc, “The Process Of Building A Virtual Teacher According To Self-Regulated Learning In Teaching Maths In Primary Schools,” Int. J. Sci. Res. Manag. IJSRM, vol. 12, no. 02, pp. 3178–3184, Feb. 2024, doi: 10.18535/ijsrm/v12i02.el02.
R. Mahendra and M. Kamayani, “Menerapkan Algoritma Neural Network Pada Chatbot Mengenai Pariwisata Di Provinsi Bangka Belitung,” vol. 7, 2023.
M. A. Nadzif, Saefurrohman, and R. Soelistijadi, “Penggunaan Teknologi Natural Language Processing dalam Sistem Chatbot untuk Peningkatan Layanan Informasi Administrasi Publik,” Indones. J. Comput. Sci., vol. 13, no. 1, Feb. 2024, doi: 10.33022/ijcs.v13i1.3645.
M. H. Nazlis, F. Insani, A. Nazir, and I. Afrianty, “Implementasi Algoritma Improve Apriori Terhadap Keluarga Beresiko Stunting,” vol. 5, no. 3, 2024.
L. A. S. Kristiyowati, F. M. Hana, and W. C. Wahyudin, “Penerapan Algoritma Naive Bayes Pada Sistem Chatbot Persewaan Kos,” vol. 22, no. 1, 2025.
Fahmi Yusron Fiddin, A. Komarudin, and M. Melina, “Chatbot Informasi Penerimaan Mahasiswa Baru Menggunakan Metode FastText dan LSTM,” J. Appl. Comput. Sci. Technol., vol. 5, no. 1, pp. 33–39, Feb. 2024, doi: 10.52158/jacost.v5i1.648.
M. R. A. F. Rifqi, Armansyah, and M. Rifqi Al Fauzan, “Kombinasi TF-IDF dan Neural Network Untuk Pelayanan Informasi Al-Qur’an Dalam Bentuk Chatbot,” J. FASILKOM, vol. 14, no. 2, pp. 318–324, Aug. 2024, doi: 10.37859/jf.v14i2.7286.
S. Zhang and J. Song, “A chatbot based question and answer system for the auxiliary diagnosis of chronic diseases based on large language model,” Sci. Rep., vol. 14, no. 1, p. 17118, Jul. 2024, doi: 10.1038/s41598-024-67429-4.
X. Sun et al., “Sentence Similarity Based on Contexts,” Trans. Assoc. Comput. Linguist., vol. 10, pp. 573–588, May 2022, doi: 10.1162/tacl_a_00477.
N. Chaturvedi and J. Dubey, “Contextual Sentence Similarity from News Articles,” Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol., vol. 10, no. 2, pp. 24–37, Mar. 2024, doi: 10.32628/CSEIT2390628.
D. Y. Dengyun Zhu, Hailong Gai, Fucheng Wan, “Semantic Similarity Caculating based on BERT,” J. Electr. Syst., vol. 20, no. 2, pp. 73–79, Apr. 2024, doi: 10.52783/jes.1099.
C. Yin and Z. Zhang, “A Study of Sentence Similarity Based on the All-minilm-l6-v2 Model With ‘Same Semantics, Different Structure’ After Fine Tuning,” in Proceedings of the 2024 2nd International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2024), vol. 115, Y. Wang, Ed., in Advances in Computer Science Research, vol. 115. , Dordrecht: Atlantis Press International BV, 2024, pp. 677–684. doi: 10.2991/978-94-6463-540-9_69.
G. W. Wicaksono, S. F. Al Asqalani, Y. Azhar, N. P. Hidayah, and A. Andreawana, “Automatic Summarization of Court Decision Documents over Narcotic Cases Using BERT,” JOIV Int. J. Inform. Vis., vol. 7, no. 2, p. 416, May 2023, doi: 10.30630/joiv.7.2.1811.
S. Bano, S. Khalid, N. M. Tairan, H. Shah, and H. A. Khattak, “Summarization of scholarly articles using BERT and BiGRU: Deep learning-based extractive approach,” J. King Saud Univ. - Comput. Inf. Sci., vol. 35, no. 9, p. 101739, Oct. 2023, doi: 10.1016/j.jksuci.2023.101739.
P. Howlader, P. Paul, M. Madavi, L. Bewoor, and V. S. Deshpande, “Fine Tuning Transformer Based BERT Model for Generating the Automatic Book Summary,” Int. J. Recent Innov. Trends Comput. Commun., vol. 10, no. 1s, pp. 347–352, Dec. 2022, doi: 10.17762/ijritcc.v10i1s.5902.
Ashwini Mandale-Jadhav, Neeraj Sharma, Ms. Deepali Ramesh, Kamble, Mr. Nilesh Ashokrao, and Thorat, “Text Summarization Using Natural Language Processing,” J Electr. Syst., vol. 20, no. 11s, pp. 3410–3417, 2024, doi: https://doi.org/10.52783/jes.8092.
O. Choudhary, H. Nehra, S. Saraswat, and K. Ahuja, “Aautomatic Text Summarization Using Deep Learning and NLP Model”.
A. Lawson McLean and V. Hristidis, “Evidence-Based Analysis of AI Chatbots in Oncology Patient Education: Implications for Trust, Perceived Realness, and Misinformation Management,” J. Cancer Educ., Feb. 2025, doi: 10.1007/s13187-025-02592-4.
D. P. Venkatesan, “Query Suggestions with Medical Data Formulation using Ontology,” vol. 12, no. 03, 2023.
S. Aghaei, K. Angele, E. Huaman, G. Bushati, M. Schiestl, and A. Fensel, “Interactive Search on the Web: The Story So Far,” Information, vol. 13, no. 7, p. 324, Jul. 2022, doi: 10.3390/info13070324.
B. Li, X. Liu, and R. Zhang, “Employing the BERT model for sentiment analysis of online commentary,” Appl. Comput. Eng., vol. 32, no. 1, pp. 241–247, Jan. 2024, doi: 10.54254/2755-2721/32/20230218.
A. Aljabar and B. M. Karomah, “Mengungkap Opini Publik: Pendekatan BERT-based- caused untuk Analisis Sentimen pada Komentar Film,” vol. 5, no. 1, 2024.
A. P. Widyassari et al., “Review of automatic text summarization techniques & methods,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 4, pp. 1029–1046, Apr. 2022, doi: 10.1016/j.jksuci.2020.05.006.
W. Liu, Y. Gao, J. Li, and Y. Yang, “A Combined Extractive With Abstractive Model for Summarization,” IEEE Access, vol. 9, pp. 43970–43980, 2021, doi: 10.1109/ACCESS.2021.3066484.
Supiyanto Supiyanto and Sriyono Sriyono, “Metode Cosine Similarity Untuk Mendeteksi Kemiripan Pada Dokumen Teks,” SAINS J. MIPA Dan Pengajarannya, vol. 1, no. 1, pp. 001–007, 2023, doi: https://doi.org/10.31957/sains.v23i1.3661.
H. Margono, D. Bastian, and N. A. Faiza, “Narrative literature review: Efficiency enhancement - user trust in chatbots as a tool for improving service quality by humans,” J. Soft Comput. Explor., vol. 5, no. 2, pp. 107–114, May 2024, doi: 10.52465/joscex.v5i2.286.
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Muhammad Ghazali Awaluddin, Muhammad Aksa, Reza Arifky, Muhammad Fajar Bakri, Dewi Fatmarani Surianto, Marwan Ramdhany Edy, Satria Gunawan Zain

This work is licensed under a Creative Commons Attribution 4.0 International License.





