1 Hit in 6.1 sec

Twitch Plays Pokemon, Machine Learns Twitch: Unsupervised Context-Aware Anomaly Detection for Identifying Trolls in Streaming Data [article]

Albert Haque
2019 arXiv   pre-print
A user whose features significantly differ from the norm will be classified as a troll. We collected 38 million data points from the viral Internet fad, Twitch Plays Pokemon.  ...  In this paper, we consider the problem of detecting and identifying Internet trolls, almost all of which are human agents.  ...  First, we propose a set of features used for identifying trolls in the viral, croudsourced Internet game, Twitch Plays Pokemon (Twitch, 2014) .  ... 
arXiv:1902.06208v1 fatcat:okvhcuq4tzefzeeboje563wyrq