1. Home
  2. Vol 13, No 1
  3. Saputra

Question Answering Al-Qur’an Menggunakan Generative Pre-Trained Transformer 3.5 Berbasis Chatbot Telegram

Elvino Dwi Saputra(1),Nazruddin Safaat Harahap(2*),Jasril Jasril(3),Yusra Yusra(4)
(1) 
(2) Universitas Islam Negeri Sultan Syarif Kasim Riau
(3) Universitas Islam Negeri Sultan Syarif Kasim Riau
(4) Universitas Islam Negeri Sultan Syarif Kasim Riau
(*) Corresponding Author
DOI : 10.35889/jutisi.v13i1.1879

Abstract

The Al-Qur’an is a holy book that regulates everything related to life in this world and the afterlife. Searching for and understanding certain information in the Qur’an took a long time. Because it contains 30 juz, 114 surahs, and 6326 verses. However, with technological development, the search and understanding process can be faster by utilizing Artificial Intelligence (AI). Because AI can do what humans do with a faster and more accurate process. Combining AI with a Question Answering System (QAS) using a chatbot solves this problem. The searching and understanding process could be done quickly and accurately in two directions. Generative Pre-trained Transformer (GPT) is used as a model to understand natural human language. This model is considered accurate and fast, with the time needed approximately 1 minute to get an answer with an accuracy of 78.85%, answer relevance of 98.3%, and hallucination of 22.5%.

Keywords: Al-Qur’an; Artificial Intelligence; Chatbot; Question Answering System; Generative Pre-trained Transformer

Abstrak

Al-Qur’an merupakan kitab suci yang didalamnya mengatur segala hal terkait kehidupan di dunia dan akhirat. Dibutuhkan waktu yang begitu lama dalam proses pencarian dan pemahaman mengenai informasi tertentu dalam Al-Qur’an. Dikarenakan didalamya terkandung 30 juz, 114 surah, dan 6326 ayat. Namun dengan adanya perkembangan teknologi proses pencarian dan pemahaman bisa lebih cepat dengan memanfaatkan Artificial Intelligence (AI). Ini dikarenakan AI dapat melakukan pekerjaan layaknya manusia dengan proses yang lebih cepat dan akurat. Perpaduan antara AI dengan Question Answering System (QAS) menggunakan chatbot menjadi solusi dari masalah tersebut. Proses pencarian dan pemahaman dapat dilakukan dengan cepat dan akurat serta dapat dilakukan dengan dua arah. Generative Pre-trained Transformer (GPT) digunakan sebagai model dalam proses pemahaman bahasa manusia secara alami. Penggunaan model ini dinilai akurat dan cepat dengan waktu yang dibutuhkan lebih kurang 1 menit untuk mendapatkan jawaban dengan akurasi sebesar 78,85%, answer relevancy sebesar 98,3% dan hallucination sebesar 22,5%.

 

Keywords


Al-Qur’an; Artificial Intelligence; chatbot; Question Answering System; Generative Pre-trained Transformer

References


D. Apriliani, S. F. Handayani, T. N. Anugrahaeni, A. Miftahudin, L. Nurarifiah, and I. T. Saputra, “Aplikasi Question Answer Sebagai Media Pembelajaran Interaktif Untuk Mata Pelajaran Akuntansi,” JMM (Jurnal Masy. Mandiri), vol. 7, no. 2, pp. 2003–2011, 2023, doi: 10.31764/jmm.v7i2.13867.

M. Sidik, B. Gunawan, and D. Anggraini, “Pembuatan Aplikasi Chatbot Kolektor dengan Metode Extreme Programming dan Strategi Forward Chaining,” J. Teknol. Inf. dan Ilmu Komput., vol. 8, no. 2, pp. 293–302, 2021, doi: 10.25126/jtiik.2021824298.

T. N. Fitria, “Artificial intelligence (AI) technology in OpenAI ChatGPT application: A review of ChatGPT in writing English essay,” ELT Forum J. English Lang. Teach., vol. 12, no. 1, pp. 44–58, 2023, doi: 10.15294/elt.v12i1.64069.

N. I. Purwita, M. A. Bijaksana, K. M. Lhaksmana, and M. Z. Naf’an, “Typo handling in searching of quran verse based on phonetic similarities,” Regist. J. Ilm. Teknol. Sist. Inf., vol. 6, no. 2, pp. 130–140, 2020, doi: 10.26594/register.v6i2.2065.

I. Humaini, T. Yusnitasari, L. Wulandari, D. Ikasari, and H. Dutt, “Informatian Retrieval of Indonesian Translated version of Al Quran and Hadith Bukhori Muslim,” 2018 Int. Conf. Sustain. Energy, Electron. Comput. Syst. SEEMS 2018, pp. 1–5, 2019, doi: 10.1109/SEEMS.2018.8687330.

Y. H. Chen, E. J. L. Lu, and Y. Y. Lin, “Efficient SPARQL Queries Generator for Question Answering Systems,” IEEE Access, vol. 10, no. September, pp. 99850–99860, 2022, doi: 10.1109/ACCESS.2022.3206794.

R. A. Yunmar and I. W. W. Wisesa, “Pengembangan Mobile-Based Question Answering System Mobile-Based Question Answering System Development With Ontology Based Knowledge,” J. Teknol. Inf. dan Ilmu Komput., vol. 7, no. 4, pp. 693–700, 2020, doi: 10.25126/jtiik.202072255.

F. Ishlakhuddin, Y. M. Santosa, and N. B. Nugraha, “Document Generation untuk Chatbot Berbasis Aturan dengan Pendekatan Template Method,” J. Inform. J. Pengemb. IT, vol. 7, no. 3, pp. 194–198, 2022, doi: 10.30591/jpit.v7i3.5098.

L. Anindyati, “Analisis dan Perancangan Aplikasi Chatbot Menggunakan Framework Rasa dan Sistem Informasi Pemeliharaan Aplikasi (Studi Kasus: Chatbot Penerimaan Mahasiswa Baru Politeknik Astra),” J. Teknol. Inf. dan Ilmu Komput., vol. 10, no. 2, pp. 291–300, 2023, doi: 10.25126/jtiik.20231026409.

R. Malhas, W. Mansour, and T. Elsayed, “Qur ’ an QA 2022 : Overview of The First Shared Task on Question Answering over the Holy Qur ’ an,” no. June, pp. 79–87, 2022.

F. Ishlakhuddin, A. Basir, and N. Nurlaela, “Rancang Bangun Sistem Tanya-jawab Berbasis Aturan STMIK Muhammadiyah Paguyangan Brebes dengan Menggunakan Telegram Chatbot,” J. Inform. J. Pengemb. IT, vol. 5, no. 3, pp. 100–105, 2020, doi: 10.30591/jpit.v5i3.2900.

W. Alshammari and S. Alhumoud, “TAQS: An Arabic Question Similarity System Using Transfer Learning of BERT with BiLSTM,” IEEE Access, vol. 10, no. September, pp. 91509–91523, 2022, doi: 10.1109/ACCESS.2022.3198955.

P. Maddigan and T. Susnjak, “Chat2VIS: Generating Data Visualizations via Natural Language Using ChatGPT, Codex and GPT-3 Large Language Models,” IEEE Access, vol. 11, no. May, pp. 45181–45193, 2023, doi: 10.1109/ACCESS.2023.3274199.

T. A. Zuraiyah et al., “Impelementasi Chatbot Pada Pendaftaran Mahasiswa Baru Menggunakan Recurrent Neural Network,” J. Ilm. Teknol. dan Rekayasa, vol. 24, no. 2, pp. 91–101, 2019.

G. Langdale and D. Lemire, “Parsing gigabytes of JSON per second,” VLDB J., vol. 28, no. 6, pp. 941–960, 2019, doi: 10.1007/s00778-019-00578-5.

O. Topsakal and T. C. Akinci, “Creating Large Language Model Applications Utilizing LangChain: A Primer on Developing LLM Apps Fast,” Int. Conf. Appl. Eng. Nat. Sci., vol. 1, no. 1, pp. 1050–1056, 2023, doi: 10.59287/icaens.1127.

Candra Wijayanto and Yeremia Alfa Susetyo, “Implementasi Flask Framework Pada Pembangunan Aplikasi Sistem Informasi Helpdesk (SIH),” JIPI (Jurnal Ilm. Penelit. dan Pembelajaran Inform., vol. 07, no. 03, pp. 858–868, 2022, [Online]. Available: https://jurnal.stkippgritulungagung.ac.id/index.php/jipi/article/view/3161/1328.

B. P. Putra and Y. A. Susetyo, “Implementasi Api Master Store Menggunakan Flask, Rest Dan Orm Di Pt Xyz,” Sistemasi, vol. 9, no. 3, pp. 543–556, 2020, doi: 10.32520/stmsi.v9i3.899.

Z. Liang, Z. Liang, Y. Zheng, B. Liang, and L. Zheng, “Data analysis and visualization platform design for batteries using flask-based python web service,” World Electr. Veh. J., vol. 12, no. 4, pp. 187–198, 2021, doi: 10.3390/wevj12040187.

M. Sarosa, M. Kusumawardani, A. Suyono, and Z. Sari, “Implementasi Chatbot Pembelajaran Bahasa Inggris menggunakan Media Sosial,” J. Edukasi dan Penelit. Inform., vol. 6, no. 3, pp. 317–322, 2020, doi: 10.26418/jp.v6i3.43191.

C. Ukamaka Betrand, O. Uzoamaka Ekwealor, and C. Juliet Onyema, “Artificial Intelligence Chatbot Advisory System,” Int. J. Intell. Inf. Syst., vol. 12, no. March, pp. 1–9, 2023, doi: 10.11648/j.ijiis.20231201.11.

A. F. K. Sibero and A. Murdani, “Sistem Informasi Desa Menggunakan Telegram Bot Sebagai Antar Muka,” J. Indones. Manaj. Inform. dan Komun., vol. 4, no. 1, pp. 206–211, 2023, doi: 10.35870/jimik.v4i1.161.

X. Yang et al., “A large language model for electronic health records,” npj Digit. Med., vol. 5, no. 1, pp. 1–9, 2022, doi: 10.1038/s41746-022-00742-2.

I. A. Bernstein et al., “Comparison of Ophthalmologist and Large Language Model Chatbot Responses to Online Patient Eye Care Questions,” JAMA Netw. open, vol. 6, no. 8, p. e2330320, 2023, doi: 10.1001/jamanetworkopen.2023.30320.

DeepEval, “DeepEval - The open-source LLM evaluation framework,” DeepEval, 2024. https://docs.confident-ai.com/ (accessed Mar. 15, 2024).

H. Afzal and T. Mukhtar, “Semantically Enhanced Concept Search of the Holy Quran: Qur’anic English WordNet,” Arab. J. Sci. Eng., vol. 44, no. 4, pp. 3953–3966, 2019, doi: 10.1007/s13369-018-03709-2.

E. Mursidah, L. Ambarwati, and F. A. Karima, “Implementasi Chatbot Layanan Informasi Pendaftaran Mahasiswa Baru Program Pascasarjana Departemen Teknik Informatika ITS,” J. Ilm. NERO, vol. 7, no. 1, pp. 43–52, 2022.

H. Toba and B. Wijaya, “Implementasi Sistem Tanya Jawab Berbasis Skenario untuk Mendukung Proses Akademik dengan IBM Watson Assistant,” J. Edukasi dan Penelit. Inform., vol. 6, no. 2, pp. 154–166, 2020, doi: 10.26418/jp.v6i2.40715.


The PDF file you selected should load here if your Web browser has a PDF reader plug-in installed (for example, a recent version of Adobe Acrobat Reader).

If you would like more information about how to print, save, and work with PDFs, Highwire Press provides a helpful Frequently Asked Questions about PDFs.

Alternatively, you can download the PDF file directly to your computer, from where it can be opened using a PDF reader. To download the PDF, click the Download link above.

Fullscreen Fullscreen Off

Full Text: File PDF

How To Cite This :

Refbacks

  • There are currently no refbacks.