Page MenuHomePhabricator

[Objective 3.1.2] Models for sockpuppet and toxic discussion detection
Closed, ResolvedPublic

Description

About:

Prototype new models to facilitate sockpuppet detection and the classification of toxic discussions (the corresponding section of the annual plan)

Subtasks:

  • Sockpuppet detection model (a) T171635
  • Better labeled data on toxic conversation structure and attacks (b) T175666

People:

Dependencies:

  • Community Tech
  • Scoring Platform (potentially on (a) TODO: check expectations with @Halfak
  • External collaborations Srijan (a), Jigsaw (b), Cornell (b) (3.1.1 preliminary data)

Estimated quarter(s):

  • Q1-Q2 (b)
  • Q2-Q3 (a)

Related Objects

Event Timeline

@DarTar should we assign this Epic task to you?

leila created subtask Unknown Object (Task).Sep 5 2017, 11:21 PM
DarTar renamed this task from [Objective 3.1.2] Models for sockpuppet and toxic language detection to [Objective 3.1.2] Models for sockpuppet and toxic discussion detection.Nov 1 2017, 6:48 PM