Application of the Benford’s law to Social bots and Information Operations activities

Lale Madahali, Margeret Hall

Publication: Chapter in book/Conference proceedingContribution to conference proceedings

Abstract

Benford's law shows the pattern of behavior in normal systems. It states that in natural systems digits' frequency have a certain pattern such that the occurrence of first digits in numbers are unevenly distributed. In systems with natural behavior, numbers begin with a “1” are more common than numbers beginning with “9”. It implies that if the distribution of first digits deviate from the expected distribution, it is indicative of fraud. It has many applications in forensic accounting, stock markets, finding abnormal data in survey data, and natural science. We investigate whether social media bots and Information Operations activities are conformant to the Benford's law. Our results showed that bots' behavior adhere to Benford's law, suggesting that using this law helps in detecting malicious online automated accounts and their activities on social media. However, activities related to Information Operations did not show consistency in regards to Benford's law. Our findings shedlight on the importance of examining regular and anomalous online behavior to avoid malicious and contaminated content on social media.
Original languageEnglish
Title of host publication2020 International Conference on Cyber Situational Awareness, Data Analytics and Assessment (CyberSA)
Editors n/a
Place of PublicationOnline
PublisherIEEE
Pages1 - 8
ISBN (Print)9781728166919
Publication statusPublished - 2020

Austrian Classification of Fields of Science and Technology (ÖFOS)

  • 102

Cite this