Difference between revisions of "A Case Study of Sockpuppet Detection in Wikipedia"
(A Case Study of Sockpuppet Detection in Wikipedia - basic info) |
(Int.links) |
||
| Line 1: | Line 1: | ||
| − | '''A Case Study of Sockpuppet Detection in Wikipedia''' - scientific work related to Wikipedia quality published in 2013, written by Thamar Solorio, Ragib Hasan and Mainul Mizan. | + | '''A Case Study of Sockpuppet Detection in Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2013, written by [[Thamar Solorio]], [[Ragib Hasan]] and [[Mainul Mizan]]. |
== Overview == | == Overview == | ||
| − | This paper presents preliminary results of using authorship attribution methods for the detection of sockpuppeteering in Wikipedia. Sockpuppets are fake accounts created by malicious users to bypass Wikipedia’s regulations. Authors dataset is composed of the comments made by the editors on the talk pages. To overcome the limitations of the short lengths of these comments, authors use an voting scheme to combine predictions made on individual user entries. Authors show that this approach is promising and that it can be a viable alternative to the current human process that Wikipedia uses to resolve suspected sockpuppet cases. | + | This paper presents preliminary results of using authorship attribution methods for the detection of sockpuppeteering in [[Wikipedia]]. Sockpuppets are fake accounts created by malicious users to bypass Wikipedia’s regulations. Authors dataset is composed of the comments made by the editors on the [[talk pages]]. To overcome the limitations of the short lengths of these comments, authors use an voting scheme to combine predictions made on individual user entries. Authors show that this approach is promising and that it can be a viable alternative to the current human process that Wikipedia uses to resolve suspected sockpuppet cases. |
Revision as of 00:13, 27 October 2019
A Case Study of Sockpuppet Detection in Wikipedia - scientific work related to Wikipedia quality published in 2013, written by Thamar Solorio, Ragib Hasan and Mainul Mizan.
Overview
This paper presents preliminary results of using authorship attribution methods for the detection of sockpuppeteering in Wikipedia. Sockpuppets are fake accounts created by malicious users to bypass Wikipedia’s regulations. Authors dataset is composed of the comments made by the editors on the talk pages. To overcome the limitations of the short lengths of these comments, authors use an voting scheme to combine predictions made on individual user entries. Authors show that this approach is promising and that it can be a viable alternative to the current human process that Wikipedia uses to resolve suspected sockpuppet cases.
