Identifying gender, age and Education level by analyzing comments on Facebook

As the use of Social media spreads every day, in different stratums of the society, alongside of the beneficial usages of this type of media, some abuse of that is also rising. Some people create fake accounts with unreal information and try to cheat people in material and/or spiritual manner. Some of them pretend lower age to target child abuse or target to cheat people by pretending themselves with an opposite sex of what they really are, or showing themselves with higher education level. So identifying the real identity of people in social media can be very useful to preventing formations of e-crimes. In this study, a system developed for identifying gender, age, and education level by analyzing comments on Facebook pages. Naïve Bayes, Support Vector Machine (SVM) and K-nearest neighbor (KNN) used as classifier and the results of them compared. The Naïve Bayes classifier with an accuracy of 90.85% for Gender, 89.67% for age and 86.15% for Education level gave the best results.