Identifying Spam Activity on Public Facebook Pages

Since their emergence, online social networks (OSNs) keep gaining popularity. However, many related problems have also arisen, such as the use of fake accounts for malicious activities. In this paper, we focus on identifying spammers among users that are active public Facebook pages. We specifically interested in groups sharing similar URLs. For purpose, built an initial dataset based all content has been posted upon feed posts a set pages with high numbers subscribers. assumed pages, hundreds thousands subscribers and revolving around common attractive topic, make ideal ground spamming activity. Our first contribution paper is reliable methodology helps potential spammer non-spammer likely to be tagged as, respectively, spammers/non-spammers manual verification. aim, used features characterizing spam activity coring method. This methodology, combined human validation, successfully allowed us build non-spammers. second analysis identified accounts. found these do not display any community-like behavior they rarely interact each other, slightly more than non-spammers during late-night hours, while less daytime hours. Finally, our third proposal clustering approach detected 16 form clusters