期刊名称：International Journal of Data Mining & Knowledge Management Process
印刷版ISSN：2231-007X
电子版ISSN：2230-9608
出版年度：2016
卷号：6
期号：6
页码：17
DOI：10.5121/ijdkp.2016.6602
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：The increased use of social media in Arab regions has attracted spammers seeking new victims. Spammersuse accounts on Twitter to distribute adult content in Arabic-language tweets, yet this content is prohibitedin these countries due to Arabic cultural norms. These spammers succeed in sending targeted spam byexploiting vulnerabilities in content-filtering and internet censorship systems, primarily by using misspelledwords to bypass content filters. In this paper we propose an Arabic word correction method to address thisvulnerability. Using our approach, we achieve a predictive accuracy of 96.5% for detecting abusiveaccounts with Arabic tweets.
关键词：Arabic; Twitter; Cyber Crime; NLP; Spelling Correction; Domain Specific Lexicon; Slang; Arabic Dialects;Text Classification; Big Data.
