Early Detection of Multilingual Troll Accounts on Twitter

Lin Miao, Mark Last, Marian Litvak

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Internet troll farms have recently been employed as a powerful and prevailing weapon of information warfare. Even though different tactics may be utilized by different groups of state-sponsored trolls, our goal is to leverage identified troll data for revealing new emerging trolls generating multilingual content. In this work, we adopt a model agnostic meta-learning framework making use of previously released troll farm datasets for the early detection of newly-emerged troll accounts from identified or unidentified troll farms. The detection earliness of various models is evaluated using variable amounts of the earliest tweets from the tested accounts. To evaluate the proposed meta-model, we compare it to several classification models based on different types of account features. Our experiments demonstrate the effectiveness of the meta-model requiring as few as ten tweets to detect a troll account with an average accuracy of 94%.

Original languageEnglish
Title of host publicationProceedings of the 2022 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2022
EditorsJisun An, Chelmis Charalampos, Walid Magdy
PublisherInstitute of Electrical and Electronics Engineers
Pages378-382
Number of pages5
ISBN (Electronic)9781665456616
DOIs
StatePublished - 1 Jan 2022
Event14th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2022 - Virtual, Online, Turkey
Duration: 10 Nov 202213 Nov 2022

Publication series

NameProceedings of the 2022 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2022

Conference

Conference14th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2022
Country/TerritoryTurkey
CityVirtual, Online
Period10/11/2213/11/22

Keywords

  • Twitter
  • meta-learning
  • multilingual classification
  • troll account detection

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems
  • Information Systems and Management
  • Communication

Fingerprint

Dive into the research topics of 'Early Detection of Multilingual Troll Accounts on Twitter'. Together they form a unique fingerprint.

Cite this