Strategic Government Communication, Public Trust and Policy Acceptance in the Digital Era: Evidence from Local Governments

Abstract

The rapid expansion of digital governance has transformed how local governments communicate policies, manage citizen engagement, and build institutional legitimacy. However, policy acceptance in the digital era depends not only on the availability of online communication platforms but also on the strategic quality, credibility, responsiveness, and personalization of government messages. This paper develops a technical framework for assessing the relationship among strategic government communication, public trust, and policy acceptance in local government contexts. The study proposes a novel algorithm, the Trust-Aware Policy Communication Optimization Algorithm (TAPCOA), designed to predict and optimize citizens’ likelihood of accepting public policies based on communication clarity, sentiment polarity, message consistency, response time, citizen feedback intensity, misinformation exposure, digital engagement frequency, and institutional trust indicators. TAPCOA integrates transformer-based semantic encoding, trust-weighted sentiment analysis, adaptive feature selection, and policy acceptance probability scoring to improve prediction accuracy and communication targeting. The proposed model is compared with established machine learning and natural language processing algorithms, including Logistic Regression, Random Forest, Support Vector Machine, XGBoost, Long Short-Term Memory networks, Bidirectional Encoder Representations from Transformers, and Graph Neural Networks. Performance evaluation is conducted using accuracy, precision, recall, F1-score, area under the receiver operating characteristic curve, mean absolute error, and computational efficiency. The paper is structured to include graphical comparisons such as algorithm performance curves, trust-policy acceptance correlation graphs, digital engagement trend plots, confusion matrices, feature-importance charts, and communication effectiveness heatmaps. The expected findings demonstrate that TAPCOA produces superior predictive performance by combining semantic message interpretation with trust-sensitive behavioral indicators. The study contributes to digital governance research by presenting a computational decision-support model that enables local governments to design evidence-based communication strategies, detect declining public trust, counter misinformation, and improve policy acceptance through targeted, transparent, and responsive digital communication.