Edge intelligence‐enabled dynamic overlapping community discovery and evolution prediction in social media data streams

Edge intelligence (EI) is recognized by academia and industry as one of the key emerging technologies for future cyber-physical-social systems (CPSS), which provides ability to analyze data at edge rather than sending it cloud analysis, will be a enabler realize world trillion hyper-connected smart sensing devices. As part CPSS, online social networks are large-scale complex that consist large number network nodes links. The dynamic discovery communities, especially overlapping important understand evolution networks. However, traditional community algorithms cannot effectively discover communities in In order address this challenge, an intelligence-enabled prediction model (EIDEP) proposed article. This encompasses label propagation algorithm based extension (LPAE) algorithm, able efficiently user structures Based on LPAE interest behavior (UIBEP) incorporated our EIDEP fast yet accurate networks, considering similarity unlinked given community. performance UIBEP models validated evaluated against notable state-of-the-art algorithms, through extensive experiments conducted Twitter dataset.