As social media has increased the reach and speed of electronic word-of-mouth (eWOM), so it has intensified customers' exposure to negative eWOM. Consequently, companies increasingly suffer from massive outbursts of negative eWOM, known as online firestorms. Because of their dynamics, it is nearly impossible to stop online firestorms if their emergence is not detected promptly. However, well-founded approaches that provide automated, real-time detection are missing. We design an Online Firestorm Detector that includes an algorithm inspired by epidemiological surveillance systems. Real-world data from a firestorm suffered by Coca-Cola is used to prove the utility and validity of the proposed approach. We show that online firestorms can be reliably detected shortly after the first piece of related negative eWOM has been generated, and that the number of false alarms is low. A comparison with competing artifacts shows that the Online Firestorm Detector is superior to approaches that could be alternatively used.
