Hybrid Human-Contextual Chatbot With Continuous Model Development Using Recurrent Neural Network For Help-Desk Supporting Tool

Ahmad Saikhu, Dyah Ayu Permata Sari, Ratih Nur Esti Anggraini

Abstract


The development of chatbots is currently quite significant, considering the trend of interactive customer services 24/7. One advantage of using chatbots is reducing queues and customer waiting times. However, previous research stated that 87% of users prefer interaction with humans to solve complex problems. Therefore, this study introduced a hybrid human-contextual chatbot with sustainable model development using Recurrent Neural Network (RNN) and threshold optimization. The research proposes a cooperation framework between Artificial Intelligence (AI) and humans to optimize the workforce while maintaining the quality of the company's services. The system has a monitoring website and continuous model development to ensure the continued growth of the model. The system trial was conducted in XYZ company's IT management division in Indonesia for four weeks. The performance evaluation process uses accuracy, hand-off rate, average execution time, and average response time. Weekly performance evaluation results obtained accuracy and hand-off rate score increased, but average execution time and response time decreased every week. The decrease in execution and response time indicates a faster model performance. The highest accuracy and hand-off rate values were 0.99 and 0.98, respectively. Execution and response times get the lowest seconds at 0.39 seconds and 0.85 seconds, respectively.

Keywords


Cooperation Framework; Supporting Help-Desk Tool; Threshold Optimization

Full Text:

PDF PDF

References


Vaios Koumaras AFA. 5G Performance Testing of Mobile Chatbot Applications. Lecture Notes in Networks and Systems2018;p. 1–6. https://ieeexplore.ieee.org/document/8515004.

S R, Balakrishnan K. Implementation of an inquisitive chatbot for database supported knowledge bases. AcademyProceedings in Engineering Sciences 2016;41:1173–1178. https://link.springer.com/article/10.1007/s12046-016-0544-1.

L, Darima O, Bitner FMJ. Implementation of an inquisitive chatbot for database supported knowledge bases. AcademyProceedings in Engineering Sciences 2019;p. 77–103. https://link.springer.com/chapter/10.1007/978-3-319-98512-1_5.

Martinez J, Castillo D. Implementation of an inquisitive chatbot for database supported knowledge bases. Interna-tional Journal of Language and Linguistics 2015;3:67–76. https://www.sciencepublishinggroup.com/article/10.11648/j.ijll.s.2015030601.19.

Ding L, Davies D. The integration of lightweight representation and annotation for collaborative design representation.Research in Engineering Design 2009;20:185–200. https://link.springer.com/article/10.1007/s00163-009-0077-2.

Firmansyah, Ilyas M, Kasyidi R, F. Klasifikasi Kalimat Ilmiah Menggunakan Recurrent Neural Network. Prosid-ing Industrial Research Workshop and National Seminar 2020;11:488–495. https://link.springer.com/article/10.1007/s00163-009-0077-2.

Xueming, Siliang L, Zheng T, Qu FZ. Frontiers: Machines vs humans: The impact of artificial intelligence chatbot disclosureon customer purchases. Science, and undefined 2019 2019;38:937–947. https://pubsonline.informs.org/doi/10.1287/mksc.2019.1192.

patrickKeith K. AI in contact centers. Communications of the ACM 2017;60 no. 8:18–19. https://dl.acm.org/doi/10.1145/3105442.

Stefanus Christian Susetyo Harjanto ERM. The Relation Among Business Process Orientation Practices in InfluencingOrganizational Performance. IPTEK The Journal for Technology and Science 2023;34 no. 1:44. https://dl.acm.org/doi/10.1145/3105442.

Jane Cleland Huang H, Dumitru C, duan CC, Herrera. Automated support for managing feature requests in open forums.Commun ACM 2009;52 no. 10:68–74. https://dl.acm.org/doi/10.1145/1562764.1562784.

Erina, Bayu FN, Bakti K, Dyah AYP, Ary APS, Bagus MS, et al. Performance Analysis of AWS and GCP CloudProviders. 2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)2022;https://ieeexplore.ieee.org/document/9865484.

Abdullah, Nafis ASM, Saiful TM, Islam. A Deep Recurrent Neural Network with BiLSTM model for Sentiment Clas-sification. 2018 International Conference on Bangla Speech and Language Processing (ICBSLP) 2018;p. 1–4. https://ieeexplore.ieee.org/document/8554396.

Sharat, Abha S, Navya T, Shivani M, Preeti A, Nagrath. Sentiment Analysis Using Gated Recurrent Neural Networks. SNComputer Science 2020;1 no. 2. https://link.springer.com/article/10.1007/s42979-020-0076-y.

Georgios, Heri KP, Helge R, Langseth. Effective hate-speech detection in Twitter data using recurrent neural networks.Applied Intelligence 2018;48:4730–4742. https://link.springer.com/article/10.1007/s10489-018-1242-y.Gabriel ET AL. 13

Sudan, Deepak J, Hoang P, David VL, Taniar. Recurrent neural network for detecting malware. Comput Secur 2020;99.https://www.sciencedirect.com/science/article/pii/S0167404820303102?via%3Dihub.

Rajat, Pradip KB, Arghya KB, Ray. Cognitive Chatbot for Personalized Contextual Customer Service: Behind theScene and beyond the Hype. Information Systems Frontiers 2024;26:899–919. https://link.springer.com/article/10.1007/s10796-021-10168-y.

Yingzi, Chih X, Patrick HS, van Esch; I, Xu LL. AI customer service: Task complexity, problem-solving ability, andusage intention. Australasian Marketing Journal (AMJ) 2020;28 no. 4:189–199. https://journals.sagepub.com/doi/10.1016/j.ausmj.2020.03.005.

Mindi, Jun L, Senchun L, Ruiqi C, Chen C, Baihai Z, et al. A Novel Industrial Intrusion Detection Method based onThreshold-optimized CNN-BiLSTM-Attention using ROC Curve. 2020 39th Chinese Control Conference (CCC) 2020;28no. 4. https://ieeexplore.ieee.org/document/9188872.

Giovanni, Guilherme AS, de Andrade; Geovana G, Francisco RSS, João CMD, Rafael PJDC, et al. A Conversation-DrivenApproach for Chatbot Management. IEEE Access 2022;10:8474–8486. https://ieeexplore.ieee.org/document/9681834.

Addi, Lili AM, Jiang. KBot: A Knowledge Graph Based ChatBot for Natural Language Understanding over Linked Data.IEEE Access 2020;8:149220–149230. https://ieeexplore.ieee.org/document/9165716.

W, Youden J. Index for rating diagnostic tests. Cancer 1950;3 No. 1:32–35. https://acsjournals.onlinelibrary.wiley.com/doi/10.1002/1097-0142(1950)3:1%3C32::AID-CNCR2820030106%3E3.0.CO;2-3.




DOI: http://dx.doi.org/10.12962%2Fj20882033.v34i3.16869

Refbacks

  • There are currently no refbacks.


Creative Commons License

IPTEK Journal of Science and Technology by Lembaga Penelitian dan Pengabdian kepada Masyarakat, ITS is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Based on a work at https://iptek.its.ac.id/index.php/jts.