TY - GEN
T1 - Multiclass SMS message categorization
T2 - 9th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2017
AU - Dewi, Fatia Kusuma
AU - Fadhlurrahman, Mgs M.Rizqi
AU - Rahmanianto, Mohamad Dwiyan
AU - Mahendra, Rahmad
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2018/5/4
Y1 - 2018/5/4
N2 - SMS spam has been growing since mobile phone usage increases. Past researches on SMS spam detection only classified SMS into two categories, spam and not spam. The binary classification of SMS spam prevents the user from seeing the spam messages that they do not really hate, e.g. an advertisement from their favorite product In this paper, we propose multi-class classification of SMS into: regular, info, ads, and fraud. We use content-based (top-N unigram) as well as non-content based features. The result shows that the best accuracy is achieved by logistic regression that is 97.5 % accuracy with configuration of normalization preprocess and 4096 top-N unigram features.
AB - SMS spam has been growing since mobile phone usage increases. Past researches on SMS spam detection only classified SMS into two categories, spam and not spam. The binary classification of SMS spam prevents the user from seeing the spam messages that they do not really hate, e.g. an advertisement from their favorite product In this paper, we propose multi-class classification of SMS into: regular, info, ads, and fraud. We use content-based (top-N unigram) as well as non-content based features. The result shows that the best accuracy is achieved by logistic regression that is 97.5 % accuracy with configuration of normalization preprocess and 4096 top-N unigram features.
KW - Classification
KW - Mobile SMS
KW - Multiclass
KW - Spam
UR - http://www.scopus.com/inward/record.url?scp=85050953481&partnerID=8YFLogxK
U2 - 10.1109/ICACSIS.2017.8355035
DO - 10.1109/ICACSIS.2017.8355035
M3 - Conference contribution
AN - SCOPUS:85050953481
T3 - 2017 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2017
SP - 210
EP - 215
BT - 2017 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2017
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 28 October 2017 through 29 October 2017
ER -