基于互动仪式链理论的短视频弹幕平台用户情绪预警机制研究——以Bilibili弹幕网站为例

User Emotional Early Warning Mechanism of Short Video Bullet Chat Platform Based on Interactive Ritual Chain Theory——Take BiliBili Website as an Example

【目的/意义】短视频平台的兴起让弹幕成为公众情感交流的重要载体,构建短视频平台弹幕情绪预警机制有助于更好地把握舆情态势。【方法/过程】以互动仪式链理论为基础,建立Bilibili弹幕视频互动仪式模型,并对驱动互动仪式链形成的用户情绪设计了预警机制。构建了EGM-马尔可夫-Fisher模型,并与EGM(1,1)、EGM-马尔可夫模型的预测结果进行了精度对比,以实现较为准确的负面情绪风险预警;在预测阈值的基础上结合灰色关联分析方法,提出情绪预警分级方案。最后通过爬取Bilibili网站舆情事件数据对预警机制进行检验。【结果/结论】EGM-马尔可夫-Fisher模型的预测精度较高,其在情绪监测预警方面具有良好的适用性。结合灰色关联分析改进的分级方法预测可靠,为提升用户情感互动体验和网络空间的有效治理提供参考。【创新/局限】研究挖掘了短视频平台互动仪式中弹幕与实现情绪预警的关联,构建了预警模型,未来可针对用户主体特征深化情绪传播研究。

【Purpose/significance】The rise of short video platform makes the bullet chat important carrier of public emotional communication. The construction of bullet chat emotion warning mechanism will help to better grasp the situation of public opinion.【Method/process】Based on the interactive ritual chain theory, the Bilibili video interactive ritual model is established, and a user emotion warning mechanism is constructed. EGM-Markov-Fisher model is constructed. The prediction accuracy of the model is compared with that of EGM(1,1) and EGM Markov model to achieve more accurate public emotion risk warning. Based on the prediction threshold and combined with the grey correlation analysis method, an emotion warning classification scheme is proposed. Finally, the mechanism is tested by crawling the public opinion event data of Bilibili website.【Result/conclusion】EGM-Markov-Fisher model has the highest prediction accuracy and has good applicability in emotion monitoring and early warning. The improved classification method combined with grey correlation analysis is reliable, which provides a reference for improving user emotional interaction experience and effective governance of public opinion.【Innovation/limitation】It explores the relationship between the bullet screen and the realization of emotional early warning in the interactive ceremony of short video platform, optimizes the warning model, and can refine the research according to the characteristics of users.