A few troublemakers often spoil online environments for everyone else. An extremely disruptive type of abuser is the troll, whose malicious activities are relatively non-obvious, and thus difficult to detect and contain -- particularly by automated systems. A growing corpus of qualitative research focuses on trolling, and differentiates it from other forms of abuse; however, its findings are not directly actionable into automated systems. On the other hand, quantitative research uses definitions of "troll" that mostly fail to capture what moderators and users consider trolling. We address this gap by giving a quantitative analysis of posts, conversations, and users, specifically sanctioned for trolling in an online forum. Although trolls (unlike most other abusers) hardly stand out in a conversation e.g. in terms of vocabulary, how they interact, rather than what they contribute, provides cues of their malicious intent.

Sizing Up the Troll: A Quantitative Characterization of Moderator-Identified Trolling in an Online Forum

SAMORY, MATTIA;
2017

Abstract

A few troublemakers often spoil online environments for everyone else. An extremely disruptive type of abuser is the troll, whose malicious activities are relatively non-obvious, and thus difficult to detect and contain -- particularly by automated systems. A growing corpus of qualitative research focuses on trolling, and differentiates it from other forms of abuse; however, its findings are not directly actionable into automated systems. On the other hand, quantitative research uses definitions of "troll" that mostly fail to capture what moderators and users consider trolling. We address this gap by giving a quantitative analysis of posts, conversations, and users, specifically sanctioned for trolling in an online forum. Although trolls (unlike most other abusers) hardly stand out in a conversation e.g. in terms of vocabulary, how they interact, rather than what they contribute, provides cues of their malicious intent.
2017
Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems
File in questo prodotto:
File Dimensione Formato  
3025453.3026007 (1).pdf

non disponibili

Tipologia: Versione dell'editore
Licenza: Accesso chiuso-personale
Dimensione 1.07 MB
Formato Adobe PDF
1.07 MB Adobe PDF   Visualizza/Apri

I documenti in ARCA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10278/5127031
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 6
social impact