Detecting harassment in real-time as conversations develop

Wessel Stoop, Florian Kunneman, A. van den Bosch, Benjamin Miller

Research output: Chapter in book/volumeContribution to conference proceedingsScientificpeer-review


We developed a machine-learning-based method to detect video game players that harass teammates or opponents in chat earlier in the conversation. This real-time technology would allow gaming companies to intervene during games, such as issue warnings or muting or banning a player. In a proof-of-concept experiment on League of Legends data we compute and visualize evaluation metrics for a machine learning classifier as conversations unfold, and observe that the optimal precision and recall of detecting toxic players at each moment in the conversation depends on the confidence threshold of the classifier: the threshold should start low, and increase as the conversation unfolds. How fast this sliding threshold should increase depends on the training set size.
Original languageEnglish
Title of host publicationProceedings of the Third Workshop on Abusive Language Online
Place of PublicationFlorence, Italy
PublisherAssociation for Computational Linguistics (ACL)
Publication statusPublished - 01 Aug 2019


Dive into the research topics of 'Detecting harassment in real-time as conversations develop'. Together they form a unique fingerprint.

Cite this