Implementasi Chatbot FAQ pada Aplikasi Monev Kinerja Direktorat Jenderal Anggaran Menggunakan Framework Rasa Open Source


Authors

  • Arif Rachman Universitas Gunadarma, Depok, Indonesia
  • Iffatul Mardhiyah Universitas Gunadarma, Depok, Indonesia
  • Miftahul Jannah Universitas Gunadarma, Depok, Indonesia

DOI:

https://doi.org/10.30865/klik.v4i1.1020

Keywords:

Chatbot; FAQ; Natural Language Processing; Rasa Open Source; Application Programming Interface

Abstract

Direktorat Jenderal Anggaran (DJA) is an organizational unit within the Ministry of Finance with the task of providing an information system related to budgeting performance. The dynamics of policy changes that have occurred recently have resulted in changes to the information system that has been developed by DJA. DJA has socialized the existing business processes and systems, but many users still ask questions through the DJA customer service channel which can only respond during business hours. This research will propose a solution for optimizing these services by creating a chatbot based on Natural Language Processing using the Rasa Open Source framework, which will be installed on one of the DJA's core systems, namely the Performance Monitoring and Evaluation Application. The chatbot will spontaneously answer user questions related to the application. The data used in this study are Frequently Asked Questions (FAQ) data, knowledge base Kemenkeupedia, Focus Group Discussions (FGD) and Performance Monev Application data taken via the API (Application Programming Interface). The results of this study are Chatbot FAQs embedded in the performance monitoring and evaluation application. The intent prediction test produces an accuracy value of 0.986, a weighted precision value of 0.973, a recall of 0.986, and an f1-score of 0.980 then the response prediction produces an accuracy value of 0.980, a weighted precision value of 0.986, a recall of 0.980, and an f1-score of 0.980. This shows that the chatbot is able to identify intent very well and respond appropriately to the user.

Downloads

Download data is not yet available.

References

Peraturan Menteri Keuangan Republik Indonesia, “Peraturan Menteri Keuangan Republik Indonesia Nomor 22/PMK.02/2021 tentang Pengukuran dan Evaluasi Kinerja Anggaran atas Pelaksanaan Rencana Kerja dan Anggaran Kementerian Negara/Lembaga,” Jakarta, 2021. [Online]. Available: www.jdih.kemenkeu.go.id

A. Kaplan and M. Haenlein, “Siri, Siri, in my hand: Who’s the fairest in the land? On the interpretations, illustrations, and implications of artificial intelligence,” Bus Horiz, vol. 62, no. 1, pp. 15–25, Jan. 2019, doi: 10.1016/j.bushor.2018.08.004.

S. Vajjala, B. Majumder, A. Gupta, and H. Surana, “Practical Natural Language Processing A Comprehensive Guide to Building Real-World NLP Systems,” 2020.

Achmad Musyaffa Taufiqi, Membangun Mesin Percakapan Pintar dengan Python dan Telegram Bot. Deepublish, 2021.

S. Mulyatun, H. Utama, and A. Mustopa, “PENDEKATAN NATURAL LANGUAGE PROCESSING PADA APLIKASI CHATBOT SEBAGAI ALAT BANTU CUSTOMER SERVICE,” 2021.

V. Boddula, A. Rao Polkampally, S. Sohail, and S. Sumair Pasha, “CHATBOT USING RASA,” 2022. [Online]. Available: www.irjmets.com

R. Vannala, S. B. Swathi, and Y. Puranam, “AI Chatbot For Answering FAQ’s,” in 2022 IEEE 2nd International Conference on Sustainable Energy and Future Electric Transportation (SeFeT), IEEE, Aug. 2022, pp. 1–5. doi: 10.1109/SeFeT55524.2022.9908774.

F. Sethi, “FAQ (Frequently Asked Questions) ChatBot for Conversation,” International Journal of Computer Sciences and Engineering Open Access Research Paper, vol. 8, no. 10, 2020, doi: 10.26438/ijcse/v8i10.710.

K. Lee, J. Jo, J. Kim, and Y. Kang, “Can Chatbots Help Reduce the Workload of Administrative Officers? - Implementing and Deploying FAQ Chatbot Service in a University,” in Communications in Computer and Information Science, Springer Verlag, 2019, pp. 348–354. doi: 10.1007/978-3-030-23522-2_45.

X. Kong and G. Wang, Conversational AI with Rasa?: build, automate, and deploy AI-powered text and voice-based assistants and chatbots. 2021.

A. Jiao, “An Intelligent Chatbot System Based on Entity Extraction Using RASA NLU and Neural Network,” J Phys Conf Ser, vol. 1487, no. 1, p. 012014, Mar. 2020, doi: 10.1088/1742-6596/1487/1/012014.

S. Singh and S. Singh, “EasyChair Preprint Effective Analysis of Chatbot Frameworks: RASA and Dialogflow Effective Analysis of Chatbot Frameworks: RASA and Dialogflow,” 2022. [Online]. Available: https://rasa.com/

Zein Hanni Pradana, Hanin Nafi’ah, and Raditya Artha Rochmanto, “Chatbot-based Information Service using RASA Open-Source Framework in Prambanan Temple Tourism Object,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 6, no. 4, pp. 656–662, Aug. 2022, doi: 10.29207/resti.v6i4.3913.

I. K. R. A. Arthana, L. J. E. D. Dewi, K. A. Seputra, and N. W. Marti, “Undiksha Virtual Assistant (Shavira)?: Integration Frequency Asked Question with Rasa Framework,” 2021.

D. G. S. Ruindungan and A. Jacobus, “Chatbot Development for an Interactive Academic Information Services using the Rasa Open Source Framework,” Jurnal Teknik Elektro dan Komputer, vol. 10, 2021.

V. Yasin, “Tools Rekayasa Perangkat Lunak dalam Membuat Pemodelan Desain Menggunakan Unified Modeling Language (UML),” TRIDHARMADIMAS: Jurnal Pengabdian Kepada Masyarakat Jayakarta, vol. 1, no. 2, p. 139, Dec. 2021, doi: 10.52362/tridharmadimas.v1i2.666.

S. Jonnada and J. K. Joy, “Measure your API Complexity and Reliability,” in 2019 IEEE 17th International Conference on Software Engineering Research, Management and Applications (SERA), IEEE, May 2019, pp. 104–109. doi: 10.1109/SERA.2019.8886790.

C. Chandrasekara and P. Herath, “Creating and Using YAML Build Pipelines,” in Hands-on Azure Pipelines, Berkeley, CA: Apress, 2020, pp. 123–142. doi: 10.1007/978-1-4842-5902-3_8.

Y. Dwi Wijaya and M. Wardah Astuti, “Pengujian Blackbox Sistem Informasi Penilaian Kinerja Karyawan Pt Inka (Persero) Berbasis Equivalence Partitions Blackbox Testing Of Pt Inka (Persero) Employee Performance Assessment Information System Based On Equivalence Partitions,” Jurnal Digital Teknologi Informasi, vol. 4, p. 2021, 2021.

Rasa Technologies GmbH, “Testing Your Assistant.” https://rasa.com/docs/rasa/testing-your-assistant/ (accessed Jul. 13, 2023).


Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Implementasi Chatbot FAQ pada Aplikasi Monev Kinerja Direktorat Jenderal Anggaran Menggunakan Framework Rasa Open Source

Dimensions Badge

ARTICLE HISTORY


Published: 2023-08-10
Abstract View: 440 times
PDF Download: 402 times