Large-scale analysis of grooming in modern social networks

作者：

Highlights：

• We release a dataset of verbal and non-verbal interactions in Social Live Streaming.

• We analyse the basic characteristics of the verbal content of this dataset.

• We illustrates how predatory behaviour bypasses the filters of service providers.

• We identify chats where grooming is performed.

• We show that it is possible to identify illegal actions, such as grooming of minors.

摘要

•We release a dataset of verbal and non-verbal interactions in Social Live Streaming.•We analyse the basic characteristics of the verbal content of this dataset.•We illustrates how predatory behaviour bypasses the filters of service providers.•We identify chats where grooming is performed.•We show that it is possible to identify illegal actions, such as grooming of minors.

论文关键词：Online grooming,Social networks,LDA,Text analysis,Emoji

论文评审过程：Received 1 April 2020, Revised 15 December 2020, Accepted 28 February 2021, Available online 6 March 2021, Version of Record 2 April 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114808