+Advanced Search

A Fast Water-army Account Detection Algorithm on BBS
Author:
Affiliation:

Fund Project:

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
    Abstract:

    This paper proposed a new water army accounts detection algorithm by analyzing the water army posting behaviors on online forums. The algorithm has three steps. The first one is to locate the suspicious periods by analyzing the daily reply behaviors of forum users, the second one is to build user collaborative networks based on user reply behaviors, and to locate the most suspicious periods by analyzing the pruned user collaborative networks, the last step is to detect the real water army accounts by analyzing the users' reply times. This algorithm excluding normal users and shrinking calculation ranges for 3 times has a small amount of calculation and high speed. We used this algorithm to analyze the dataset of Sina forum on 2010, and the results show that this algorithm can not only detect single water army account but also detect water army corps, and can determine the content of water army speculation.

    Reference
    Related
    Cited by
Article Metrics
  • PDF:
  • HTML:
  • Abstract:
  • Cited by:
Get Citation
History
  • Received:
  • Revised:
  • Adopted:
  • Online: April 23,2015
  • Published: