DocumentCode :
607938
Title :
Identifying gender, age and Education level by analyzing comments on Facebook
Author :
Talebi, M. ; Kose, C.
Author_Institution :
Bilgisayar Muhendisligi Bolumu, Karadeniz Teknik Univ., Trabzon, Turkey
fYear :
2013
fDate :
24-26 April 2013
Firstpage :
1
Lastpage :
4
Abstract :
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.
Keywords :
Bayes methods; computer crime; data mining; pattern classification; social networking (online); support vector machines; Facebook pages; KNN classifier; Naïve Bayes classifier; SVM; age identification; e-crimes; education level; gender identification; k-nearest neighbor classifier; real identity identification; social media; support vector machine; Blogs; Data mining; Education; Facebook; Media; Support vector machines; Twitter; Age; Education level; Facebook; Gender; SAM; Social media; text mining;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing and Communications Applications Conference (SIU), 2013 21st
Conference_Location :
Haspolat
Print_ISBN :
978-1-4673-5562-9
Electronic_ISBN :
978-1-4673-5561-2
Type :
conf
DOI :
10.1109/SIU.2013.6531599
Filename :
6531599
Link To Document :
بازگشت