Discovering geo-dependent stories by combining density-based clustering and thread-based aggregation techniques

作者：

Highlights：

• This work combines geo-clustering and content aggregation to detect unexpected behavior in a city.

• Content analysis provide explanatory information to anomalous clusters.

• Results show that the complementarity of content and geo-location is beneficial.

• Feasibility to be deployed in real scenarios.

摘要

•This work combines geo-clustering and content aggregation to detect unexpected behavior in a city.•Content analysis provide explanatory information to anomalous clusters.•Results show that the complementarity of content and geo-location is beneficial.•Feasibility to be deployed in real scenarios.

论文关键词：Data mining,Crowd detection,Density-based clustering,Content aggregation,Event detection

论文评审过程：Received 11 July 2017, Revised 8 November 2017, Accepted 9 November 2017, Available online 10 November 2017, Version of Record 16 November 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.11.019