突发事件情境下政务微博信息发布有效性评估

Evaluating the Effectiveness of Government Microblog Information Release in Emergency Situations

政府通过新媒体发布信息已经成为创新政府治理和社会服务的一个重要途径,评估政务微博信息发布有效性有助于提升大数据环境下政府舆情治理能力。从新公共管理理论出发,本研究提出基于“认知-情感-行为”理论和数据包络分析(data envelopment analysis,DEA)模型的政务微博信息发布有效性评估方法,搜集2020年与南方汛情相关的微博数据,基于劝服理论识别政务微博信息发布有效性的影响因素,建立七种回归模型,采用SHapley Additive exPlanations(SHAP)对综合表现最好的LGBMRegressor模型进行影响因素分析和交互作用分析,揭示政务微博信息发布有效性的影响机制。本研究结果为突发事件情境下增强政务微博信息发布的有效性提供了相关信息发布的建议,对提升数字化时代政务微博舆情治理能力具有重要意义。

Governments information release by the new media has become an important way to bring innovation in the field of governance and social services. Evaluating the effectiveness of information release by government microblogging helps improve the government’s ability to deal with public opinion in the big data environment. From the perspective of the new public management theory, this study proposes a method to evaluate the effectiveness of information release by government microblogging based on the“Cognition-Emotion-Behavior”theory and data envelopment analysis model. Microblog entries related to the southern flood in 2020 were collected. Thereafter, based on persuasion theory, we identified the influencing factors of the information release effectiveness of government microblogging. Seven regression models were established. The SHapley Additive exPlanations(SHAP) technique was used to analyze the importance of features and interaction of the LGBMRegressor model, which offers optimal comprehensive performance. The influencing mechanism of the effectiveness of government microblog information release is revealed. The obtained results provide numerous suggestions on enhancing the effectiveness of government microblog information release during public emergencies, which is of great significance in improving the ability of government microblogging to deal with public opinion in the digital era.