Microblogs are one of a growing group of social network tools. Twitter is, at present, one of the most popular forums for microblogging in online social networks, and the fastest growing. Fifty million messages flow through servers, computers, and cell phones on a wide variety of topics exchanged daily. With this considerable volume, Twitter is a natural and obvious target for spreading spam via the messages, called tweets. The challenge is how to determine if a tweet is a spam or not, and more specifically a special category advertising pharmaceutical products. The authors look at the essential characteristics of spam tweets and what makes microblogging spam unique from email or other types of spam. They review methods and tools currently available to identify general spam tweets. Finally, this work introduces a new methodology of applying text mining and data mining techniques to generate classifiers that can be used for pharmaceutical spam detection in the context of microblogging.
A Mapping Study to Investigate Spam Detection on Social Networks
