College of Information and Computer Engineering, Northeast Forestry University, Harbin, People's Republic of China.
Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai, People's Republic of China.
PLoS One. 2020 Oct 29;15(10):e0241355. doi: 10.1371/journal.pone.0241355. eCollection 2020.
The response of netizens toward controversial events plays an important guiding role in the development of events. Based on the identification of such responses, this study aimed to determine the critical outbreak time window of events. The microblog texts related to an event were divided into seven emotional categories via multi-emotional analysis to capture the subtle emotions of netizens toward an event, i.e., public opinion. By detecting the characteristics of the text and regional coverage of emotions, an emotional coverage index that reflects the intensity of emotional impact was proposed to determine the mainstream emotion of netizens. By capturing the mutation characteristics of the impact intensity of mainstream emotions, the critical time window of the public opinion toward the event was obtained. The experimental results demonstrated that the proposed method can effectively identify the critical outbreak time window of controversial events, which can help authorities in preventing the further aggravation of events.
网民对争议事件的反应对事件的发展起着重要的指导作用。本研究旨在通过识别这些反应，确定事件的关键爆发时间窗口。通过多情感分析将与事件相关的微博文本分为七个情感类别，以捕捉网民对事件的微妙情感，即舆论。通过检测文本特征和情感的区域覆盖，提出了一种情感覆盖指数来反映情感影响的强度，以确定网民的主流情绪。通过捕捉主流情绪影响强度的突变特征，获得了事件舆论的关键时间窗口。实验结果表明，所提出的方法可以有效地识别争议事件的关键爆发时间窗口，这有助于当局防止事件的进一步恶化。
