Indirect information linkage for OSINT through authorship analysis of aliases
The International Workshop on Data Mining Applications in Industry & Government (DMApps 2013)
In this paper we examine the problem of automatically link- ing online accounts for open source intelligence gathering.We specically aim to determine if two social media accounts are shared by the same au- thor, without the use of direct linking evidence. We prole the accounts using authorship analysis and nd the best matching guess. We apply this to a series of Twitter accounts identied as malicious by a methodology named SPOT and nd several pairs of accounts that belong to the same author, despite no direct evidence linking the two. Overall, our results show that linking aliases is possible with an accuracy of 84%, and using our automated threshold method improves our accuracy to over 90% by removing incorrectly discovered matches.