AuthCom: Authorship verification and compromised account detection in online social networks using AHP-TOPSIS embedded profiling based technique
作者：
Highlights：
• Analyzed efficiency of authorship verification for detection of compromised accounts.
• Both content-specific as well as content-free textual features were assessed.
• Implemented a profiling based technique (later upgraded with AHP-TOPSIS ranking).
• Assessed how each user maintained consistency in different set of features.
• Emphasized the fiasco of benchmarking the best set of features.
摘要
•Analyzed efficiency of authorship verification for detection of compromised accounts.•Both content-specific as well as content-free textual features were assessed.•Implemented a profiling based technique (later upgraded with AHP-TOPSIS ranking).•Assessed how each user maintained consistency in different set of features.•Emphasized the fiasco of benchmarking the best set of features.
论文关键词：Authorship verification,Compromised accounts,Online social networks,Natural language processing,AHP,TOPSIS,n-grams,Stylometry
论文评审过程：Received 26 April 2018, Revised 16 June 2018, Accepted 3 July 2018, Available online 5 July 2018, Version of Record 20 July 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.07.011
