Detecting Predatory Behaviour in Online Game Chats

Elin Rut Gudnadottir, Alaina K. Jensen, Yun-Gyung Cheong, Julian Togelius, Byung Chull Bae, Christoffer Holmgård Pedersen

Research output: Contribution to conference - NOT published in proceeding or journalPaperResearchpeer-review

Abstract

This paper describes a machine learning approach to detect
sexually predatory behaviour in the massively multiplayer online game for children, MovieStarPlanet. The goal of this work is to take a chat log as an input and outputs its label as either the predatory category or the non-predatory category. From the raw in-game chat logs provided by MovieStarPlanet, we first prepared three sub datasets via extensive preprocessing. Then, two machine learning algorithms, naive Bayes and Decision Tree, were employed to model the predatory behaviour using different feature sets. Our evaluation has revealed that the proposed
approach achieved high accuracies in detecting predatory chats
Original languageEnglish
Publication date9 Nov 2013
Number of pages11
Publication statusPublished - 9 Nov 2013
EventThe 2nd Workshop on Games and NLP: Workshop at the 6th International Conference on Interactive Digital Storytelling - Bahcesehir University Galata Campus (Animation Lab), Istanbul, Turkey
Duration: 9 Nov 20139 Nov 2013
Conference number: 6
http://gamesandnarrative.net/icids2013/call-to-participate-in-workshops

Workshop

WorkshopThe 2nd Workshop on Games and NLP
Number6
LocationBahcesehir University Galata Campus (Animation Lab)
Country/TerritoryTurkey
CityIstanbul
Period09/11/201309/11/2013
Internet address

Keywords

  • NLP
  • predator
  • game
  • text classification

Fingerprint

Dive into the research topics of 'Detecting Predatory Behaviour in Online Game Chats'. Together they form a unique fingerprint.

Cite this