Enhancing government service delivery: A case study of ACQAR implementation and lessons learned from ChatGPT integration in a Singapore government agency
This paper presents the pilot implementation of AI Based Citizen Question-Answer Recommender (ACQAR) as an attempt to enhance citizen service delivery within a Singaporean government agency. Drawing insights from previous studies on the Empath library's use in Service Level Agreement (SLA) pred...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Institutional Knowledge at Singapore Management University
2024
|
| Subjects: | |
| Online Access: | https://ink.library.smu.edu.sg/lkcsb_research/7504 https://ink.library.smu.edu.sg/context/lkcsb_research/article/8503/viewcontent/3657054.3657130.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Singapore Management University |
| Language: | English |
| Summary: | This paper presents the pilot implementation of AI Based Citizen Question-Answer Recommender (ACQAR) as an attempt to enhance citizen service delivery within a Singaporean government agency. Drawing insights from previous studies on the Empath library's use in Service Level Agreement (SLA) prediction and the implementation of the Citizen Question-Answer system (CQAS), we redesigned the pilot system, ACQAR. ACQAR integrates the outputs from Empath X SLA predictor and CQAS as essential inputs to the ChatGPT engine, creating contextually aware responses for customer service officers to use as responses to the citizens.Empath X SLA predictor anticipates the expected service response time based on citizens' emotional states, while CQAS recommends answers for faster and more efficient officer responses. This paper provides a comprehensive blueprint for governments aiming to enhance citizen service delivery by fusing sentiment analysis, SLA prediction, question-answer models, and ChatGPT. The proposed system design aims to revolutionize government-citizen interactions, delivering empathetic, efficient, and tailored responses without violating SLAs.Although the full-scale deployment of ACQAR is pending, this paper outlines a foundational step towards the practical development and implementation of an intelligent system by sharing the trial outcomes of ACQAR. By leveraging ChatGPT, this system holds the potential to significantly enhance citizen satisfaction, foster trust in government services, and strengthen overall government-citizen relationships.Additionally, the paper addresses inherent challenges associated with ChatGPT, including data opacity, potential misinformation, and occasional errors, especially critical in government decision-making. Upholding public administration's core values of transparency and accountability, the paper emphasizes the importance of AI explainability in ChatGPT's adoption within government agencies. Strategies proposed include prompt engineering, data governance, and the adoption of interpretability tools such as SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) to enhance understanding and align ChatGPT's decision-making processes with these principles. |
|---|