Large-scale analysis of grooming in modern social networks

•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. Social networks are evolving to engage their users more by providing them with more functionalities. One of the most attracting ones is streaming. Users may broadcast part of their daily lives to thousands of others world-wide and interact with them in real-time. Unfortunately, this feature is reportedly exploited for grooming. In this work, we provide the first in-depth analysis of this problem for social live streaming services. More precisely, using a dataset that we collected, we identify predatory behaviours and grooming on chats that bypassed the moderation mechanisms of the LiveMe, the service under investigation. Beyond the traditional text approaches, we also investigate the relevance of emojis in this context, as well as the user interactions through the gift mechanisms of LiveMe. Finally, our analysis indicates the possibility of grooming towards minors, showing the extent of the problem in such platforms.