Provided by: International Journal of Computer Applications
Topic: Big Data
Date Added: Nov 2012
In this paper, the authors present a social network spam detection application based on texts. Particularly, they tested on the Facebook spam. They develop an application to test the prototype of Facebook spam detection. The features for checking spams are the number of keywords, the average number of words, the text length, the number of links. The data mining model using the decision tree J48 is created using Weka. The methodology can be extended to include other attributes. The prototype application demonstrates the real use of the Facebook application.