| dc.contributor.author | Zhinan Xu | |
| dc.contributor.author | Zijun Liu | |
| dc.contributor.author | Hang Luo | |
| dc.date.accessioned | 2025-12-13T14:09:57Z | |
| dc.date.accessioned | 2026-05-22T09:51:56Z | |
| dc.date.available | 2026-05-22T09:51:56Z | |
| dc.date.issued | 2025-12-13T14:09:57Z | |
| dc.identifier.uri | https://doi.org/10.1177/21582440251317833 | |
| dc.identifier.uri | http://digilib.fisipol.ugm.ac.id/repo/handle/15717717/67836 | |
| dc.description.abstract | Addressing the challenge of accurately evaluating public policy performance in response to citizens’ diverse needs remains a significant issue in governance. Traditional methods of public policy evaluation often lack responsiveness and precision, hindering the ability of governments to achieve good governance. The introduction of a public satisfaction index into policy evaluations can drive governments to proactively address these challenges. This paper proposes a systematic and applicable online public opinion index system, utilizing artificial neural networks and big data, to enhance the accuracy and timeliness of public policy evaluations. Guided by the theory of three elements of attitude in social psychology, the index system captures the public’s attraction to specific policies, their stance, and emerging issues during policy promotion. By leveraging empirical data and a deep learning model based on convolutional neural networks (CNN), the model achieves a high accuracy of 93.40%, surpassing most comparable models. This approach offers a more scientific basis for improving government decision-making and policy performance. | |
| dc.publisher | SAGE Publishing | |
| dc.subject.lcc | History of scholarship and learning. The humanities; Social Sciences | |
| dc.title | Can Artificial Intelligence Technology Help Achieving Good Governance: A Public Policy Evaluation Method Based on Artificial Neural Network | |
| dc.type | Article | |
| dc.description.doi | 10.1177/21582440251317833 | |
| dc.title.journal | SAGE Open | |
| dc.identifier.oai | oai:doaj.org/journal:d672f1ed960446809bdd392150f2dfac | |
