当前位置: X-MOL 学术Comput. Ind. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Exploring the contagion effect of social media on mass shootings
Computers & Industrial Engineering ( IF 7.9 ) Pub Date : 2022-08-11 , DOI: 10.1016/j.cie.2022.108565
Dixizi Liu , Zhijie Sasha Dong , Guo Qiu

Social media plays a prominent role in the spread of mass shootings. Moreover, it brought about a significant contagious effect on future similar incidents. Therefore, we explore Machine Learning (ML) models to forecast the change in the public’s attitudes about mass shootings on social media over time. These ML models include Support Vector Machine (SVM), Logistic Regression (LR), and the optimized Deep Neural Networks based on an Improved Particle Swarm Optimization algorithm (IPSO-DNN). We then propose a self-excited contagion model to predict the number of mass shootings by focusing on the spread of public attitudes on Twitter. We also improve the proposed contagion model with the consideration of social distancing and the daily growth rate of COVID-19 cases, as to predict and analyze mass shootings under the COVID-19 pandemic. Experimental results demonstrate that the proposed contagion models perform very well in predicting future mass shootings in the United States.



中文翻译:

探索社交媒体对大规模枪击事件的传染效应

社交媒体在大规模枪击事件的传播中发挥着重要作用。此外,它对未来的类似事件产生了显着的传染性影响。因此,我们探索机器学习 (ML) 模型来预测公众对社交媒体大规模枪击事件的态度随时间的变化。这些机器学习模型包括支持向量机 (SVM)、逻辑回归 (LR) 和基于改进的粒子群优化算法 (IPSO-DNN) 的优化深度神经网络。然后,我们提出了一个自激传染模型,通过关注公众态度在 Twitter 上的传播来预测大规模枪击事件的数量。我们还考虑到社会距离和 COVID-19 病例的每日增长率来改进所提出的传染模型,以预测和分析 COVID-19 大流行下的大规模枪击事件。

更新日期:2022-08-11
down
wechat
bug