Graph-based clustering of extracted paraphrases for labelling crime reports
作者：
Highlights：
• Novel approach for labelling crime reports.
• Three important crime aspects are considered.
• Graph based hierarchical clustering of paraphrases is done.
• Proposed sparsity scheme is compared with edge density and Gini index based sparsity.
• The experimental results show the effectiveness of the work.
摘要
•Novel approach for labelling crime reports.•Three important crime aspects are considered.•Graph based hierarchical clustering of paraphrases is done.•Proposed sparsity scheme is compared with edge density and Gini index based sparsity.•The experimental results show the effectiveness of the work.
论文关键词：Crime analysis,Text mining,Entity recognition,Graph clustering,Clustering coefficient,Paraphrase extraction,Sparse graph,Sparsity measure,Edge density,Gini index
论文评审过程：Available online 4 May 2019, Version of Record 12 June 2019.
论文官网地址：https://doi.org/10.1016/j.knosys.2019.05.004
