Generic metadata representation framework for social-based event detection, description, and linkage
作者：
Highlights：
• Performs semantic-aware event detection, description, and linkage from social media data.
• Represents heterogeneous data in generic model made of temporal, spatial, & semantic dimensions.
• Evaluates data similarity using combined temporal, spatial, and semantic similarity measures.
• Detects events from similar social media objects using adapted unsupervised learning algorithm.
• Describes events in generic model and identifies their directional, metric & topologic relations.
摘要
•Performs semantic-aware event detection, description, and linkage from social media data.•Represents heterogeneous data in generic model made of temporal, spatial, & semantic dimensions.•Evaluates data similarity using combined temporal, spatial, and semantic similarity measures.•Detects events from similar social media objects using adapted unsupervised learning algorithm.•Describes events in generic model and identifies their directional, metric & topologic relations.
论文关键词：Social media,Metadata,Semantics,Similarity evaluation,Event detection,Event relationships,Collective knowledge
论文评审过程：Received 6 January 2019, Revised 7 May 2019, Accepted 25 June 2019, Available online 9 July 2019, Version of Record 20 January 2020.
论文官网地址：https://doi.org/10.1016/j.knosys.2019.06.025
