Big data directed acyclic graph model for real-time COVID-19 twitter stream detection

作者：

Highlights：

• A distributed Directed Acyclic Graph topology framework to aggregate and process large-scale of tweets related to COVID-19 in real-time is proposed.

• The proposed PESCAD algorithm uses the Poisson distribution to detect anomalous tweets.

• The proposed system can identify, cluster, and visualize important keywords in tweets.

摘要

•A distributed Directed Acyclic Graph topology framework to aggregate and process large-scale of tweets related to COVID-19 in real-time is proposed.•The proposed PESCAD algorithm uses the Poisson distribution to detect anomalous tweets.•The proposed system can identify, cluster, and visualize important keywords in tweets.

论文关键词：Anomaly detection,Big data,COVID-19,Directed acyclic graph,Event stream

论文评审过程：Received 28 March 2021, Revised 15 September 2021, Accepted 24 October 2021, Available online 26 October 2021, Version of Record 13 November 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108404