Detecting rumours with latency guarantees using massive streaming data

Today’s social networks continuously generate massive streams of data, which provide a valuable starting point for the detection rumours as soon they start to propagate. However, rumour faces tight latency bounds, cannot be met by contemporary algorithms, given sheer volume high-velocity streaming data emitted networks. Hence, in this paper, we argue best-effort that detects most quickly rather than all with high delay. To end, combine techniques efficient, graph-based matching patterns effective load shedding discards some input while minimising loss accuracy. Experiments large-scale real-world datasets illustrate robustness our approach terms runtime performance and accuracy under diverse conditions.